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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17552
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Anton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vat
    -0.18
    efeller
    -0.16
    ï¸
    -0.15
    ÑĥлÑİ
    -0.15
    URITY
    -0.15
    iba
    -0.15
    _sensitive
    -0.15
    leen
    -0.15
    abwe
    -0.15
    krit
    -0.15
    POSITIVE LOGITS
    nio
    0.25
    ÃŃn
    0.21
    ella
    0.21
    ello
    0.20
    ucci
    0.20
    ioni
    0.19
    ius
    0.19
    elli
    0.19
    ious
    0.19
    ios
    0.18
    Activations Density 0.010%

    No Known Activations