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. 8043
    Prev
    Next
    INDEX
    Explanations

    references to the treatment of individuals with care and respect

    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
    lico
    -0.18
    ../../../../
    -0.17
    ergus
    -0.15
    innacle
    -0.15
    alendar
    -0.15
    .digital
    -0.14
    atik
    -0.14
    theid
    -0.14
    ensual
    -0.14
    lan
    -0.14
    POSITIVE LOGITS
    557
    0.16
    old
    0.15
    -treated
    0.15
     Tone
    0.15
    orns
    0.14
     treating
    0.14
    uetype
    0.14
    ood
    0.14
    uated
    0.14
    rette
    0.14
    Activations Density 0.042%

    No Known Activations