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. 20188
    Prev
    Next
    INDEX
    Explanations

    expressions related to financial aid or support for small businesses

    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
    abei
    -0.15
    urtle
    -0.15
    igue
    -0.14
    виж
    -0.14
     dr
    -0.14
    ASI
    -0.14
    atics
    -0.14
    Ỽm
    -0.13
    etti
    -0.13
    swire
    -0.13
    POSITIVE LOGITS
    .po
    0.14
    ahlen
    0.14
    oward
    0.14
    oland
    0.14
    746
    0.14
     Stap
    0.14
    UGH
    0.14
    øre
    0.14
    -entity
    0.14
    =>$
    0.13
    Activations Density 0.009%

    No Known Activations