© 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. 31-LLAMASCOPE-RES-32K
    6. 10238
    Prev
    Next
    INDEX
    Explanations

    data related to organization representation and childcare services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    даÑĤ
    -0.14
    RuntimeObject
    -0.13
     Scientists
    -0.13
    etty
    -0.13
    ibli
    -0.12
    itis
    -0.12
    .Fat
    -0.11
     Literature
    -0.11
    ancias
    -0.11
    .paper
    -0.11
    POSITIVE LOGITS
     Enter
    0.24
     enter
    0.23
     REQUIRED
    0.23
    (required
    0.23
     OPTIONAL
    0.23
     Please
    0.23
     optional
    0.23
    (Optional
    0.22
    (optional
    0.22
     please
    0.22
    Activations Density 0.100%

    No Known Activations