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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-LLAMASCOPE-RES-32K
    6. 25242
    Prev
    Next
    INDEX
    Explanations

    contact information and phone numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rido
    -0.19
    igger
    -0.16
    891
    -0.15
    QL
    -0.15
    ieder
    -0.15
    гÑĢад
    -0.15
     tion
    -0.14
    736
    -0.14
    rego
    -0.14
    otts
    -0.14
    POSITIVE LOGITS
    folio
    0.19
     Buccane
    0.15
    istrovstvÃŃ
    0.15
    ONA
    0.15
    avail
    0.15
    udad
    0.15
    iyas
    0.15
     baÅŁÄ±na
    0.14
    ÑĪÑĥ
    0.14
     eql
    0.14
    Activations Density 0.030%

    No Known Activations