© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 7-LLAMASCOPE-RES-32K
    11. 7026
    Prev
    Next
    INDEX
    Explanations

    methods and functions related to string manipulation in programming, particularly those that check for the presence or index of substrings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zeÅĦ
    -0.18
    ssp
    -0.16
    emple
    -0.16
    EncodingException
    -0.15
    roots
    -0.14
     borderTop
    -0.14
    ÑĢаÑīениÑı
    -0.14
    icons
    -0.14
    ren
    -0.14
    éru
    -0.13
    POSITIVE LOGITS
    baugh
    0.15
     기ìŀIJ
    0.15
     Schro
    0.14
    urst
    0.14
    burgh
    0.14
    ungan
    0.14
    stor
    0.14
    @js
    0.14
     lis
    0.13
    onnement
    0.13
    Activations Density 0.048%

    No Known Activations