© 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. 16-LLAMASCOPE-RES-32K
    11. 5907
    Prev
    Next
    INDEX
    Explanations

    historical references to places and their past uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alley
    -0.15
    ients
    -0.15
     Sala
    -0.15
    upal
    -0.14
    langs
    -0.13
     Amen
    -0.13
    otte
    -0.13
    ì²ł
    -0.13
    .synthetic
    -0.13
    ynth
    -0.13
    POSITIVE LOGITS
     headquarters
    0.21
     venue
    0.18
     quarters
    0.18
    utherford
    0.18
     hosting
    0.17
     nơi
    0.17
     hub
    0.17
    quarters
    0.17
     miejs
    0.17
     мÑĸÑģÑĨе
    0.16
    Activations Density 0.151%

    No Known Activations