© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 18336
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and their associated contexts

    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
    ãģ¾ãģŁ
    -0.16
    .jp
    -0.16
    áh
    -0.14
    ordinate
    -0.14
    Bias
    -0.13
    ãĥ¼ãĥī
    -0.13
    ká
    -0.13
    olt
    -0.13
    :
    -0.13
    ement
    -0.13
    POSITIVE LOGITS
     why
    0.24
     how
    0.23
     an
    0.20
     what
    0.19
    ä¸Ģç§į
    0.18
     a
    0.18
     Part
    0.17
     How
    0.17
     Why
    0.17
     aka
    0.15
    Activations Density 0.115%

    No Known Activations