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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 1-LLAMASCOPE-RES-32K
    6. 2274
    Prev
    Next
    INDEX
    Explanations

    the presence of specific numerical values related to rankings or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marsh
    -0.15
     Newport
    -0.14
    Dlg
    -0.14
     Goose
    -0.13
    pez
    -0.13
    ilih
    -0.13
     tiá»ĥu
    -0.13
    uther
    -0.13
    ellow
    -0.13
     zero
    -0.13
    POSITIVE LOGITS
    微软éĽħé»ij
    0.15
    -urlencoded
    0.15
     ì¡
    0.14
    soc
    0.14
    аÑĢÑħ
    0.14
     Ingredients
    0.14
    elige
    0.14
     rog
    0.14
    禮
    0.14
    ighbor
    0.13
    Activations Density 0.112%

    No Known Activations