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. 26-LLAMASCOPE-RES-32K
    6. 27740
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and structures related to functions and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?family
    -0.14
    TOTYPE
    -0.13
    ãĤĵãģ¨
    -0.13
    лиÑĪком
    -0.13
    ائÙĤ
    -0.13
    acic
    -0.13
    ebo
    -0.13
    izont
    -0.13
    okino
    -0.12
    úsqueda
    -0.12
    POSITIVE LOGITS
     post
    1.53
     Post
    1.41
    post
    1.33
    Post
    1.31
    -post
    1.20
    _post
    1.16
    .post
    1.15
     POST
    1.12
    POST
    1.03
    (post
    1.02
    Activations Density 0.262%

    No Known Activations