© 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. 3-LLAMASCOPE-RES-32K
    6. 24004
    Prev
    Next
    INDEX
    Explanations

    terms related to correlation and relationships in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ew
    -0.17
    à¤¾à¤ł
    -0.17
    uko
    -0.15
    branch
    -0.15
     branch
    -0.15
     Branch
    -0.15
    akk
    -0.14
    ienne
    -0.14
    dy
    -0.14
    Branch
    -0.14
    POSITIVE LOGITS
     ÏĢε
    0.14
     ranger
    0.14
     Distance
    0.14
     digest
    0.13
    Distance
    0.13
    tes
    0.13
    @js
    0.13
    ç«ĭ
    0.13
     Dear
    0.13
    nds
    0.13
    Activations Density 0.011%

    No Known Activations