Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 7-LLAMASCOPE-RES-32K
    6. 13529
    Prev
    Next
    INDEX
    Explanations

    mentions of Twitter links or references in the text

    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
     Hayden
    -0.16
    ekk
    -0.15
     Gim
    -0.15
    élé
    -0.14
    WebHost
    -0.14
    agit
    -0.14
     paj
    -0.14
    spm
    -0.14
    URING
    -0.14
    avad
    -0.14
    POSITIVE LOGITS
    ongsTo
    0.16
    orch
    0.15
    ati
    0.15
    artial
    0.15
    orian
    0.15
    ĥn
    0.15
    umb
    0.14
    ãĥ©ãĥ³ãĤ¹
    0.14
     Cree
    0.14
    piler
    0.14
    Activations Density 0.003%

    No Known Activations