© 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. 23-LLAMASCOPE-RES-32K
    11. 15718
    Prev
    Next
    INDEX
    Explanations

    expressions of positive emotional responses and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bias
    -0.15
    enson
    -0.15
    ãģĹãģı
    -0.14
    cone
    -0.14
    zag
    -0.13
    upply
    -0.13
    idis
    -0.13
    asive
    -0.13
    fcc
    -0.13
    á¿ĸ
    -0.13
    POSITIVE LOGITS
     response
    0.56
     feedback
    0.47
     responses
    0.46
    response
    0.43
     reaction
    0.41
     Response
    0.40
    Response
    0.38
     reception
    0.36
    feedback
    0.36
     reactions
    0.36
    Activations Density 0.241%

    No Known Activations