© 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. 30-LLAMASCOPE-RES-32K
    11. 24185
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" as a preposition in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asename
    -0.14
    yk
    -0.14
    arnings
    -0.14
    enis
    -0.14
    ÅĻenÃŃ
    -0.14
    ä¹ĭ
    -0.13
    491
    -0.13
    uite
    -0.13
     Prepared
    -0.13
    δα
    -0.13
    POSITIVE LOGITS
     nutshell
    0.22
     purs
    0.21
     view
    0.21
     stip
    0.20
    course
    0.20
     conson
    0.19
     ÑĤеÑĩ
    0.19
    case
    0.18
     course
    0.18
    charge
    0.18
    Activations Density 0.263%

    No Known Activations