© 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. 20-LLAMASCOPE-RES-32K
    6. 25730
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations and councils

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ลà¸Ķ
    -0.15
     Tanner
    -0.14
     Perr
    -0.14
    rane
    -0.14
    egan
    -0.14
     Herr
    -0.14
    egov
    -0.14
     UNU
    -0.14
    ottes
    -0.13
    ulin
    -0.13
    POSITIVE LOGITS
     Manip
    0.31
     Ass
    0.25
     leh
    0.22
    Ass
    0.20
    -Ass
    0.20
     ass
    0.19
    Manip
    0.19
     Myanmar
    0.19
     manip
    0.18
     Miz
    0.17
    Activations Density 0.043%

    No Known Activations