© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 7393
    Prev
    Next
    INDEX
    Explanations

    terms related to dialog flow and session management in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urette
    -0.17
    /***/
    -0.16
    ÑĢоÑĪ
    -0.14
    ãĥ³ãĥĨãĤ£
    -0.14
    زÙħ
    -0.14
    Integral
    -0.14
    imler
    -0.14
    208
    -0.14
    using
    -0.13
    _IB
    -0.13
    POSITIVE LOGITS
    odel
    0.16
     Zwe
    0.15
    -------↵↵
    0.15
    ile
    0.14
    arges
    0.14
    ixon
    0.14
    anchor
    0.14
    ouz
    0.14
    otten
    0.14
     Jin
    0.14
    Activations Density 0.023%

    No Known Activations