© 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. 7-LLAMASCOPE-RES-32K
    11. 5958
    Prev
    Next
    INDEX
    Explanations

    references to leaked documents and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aub
    -0.16
    iane
    -0.15
     Satisfaction
    -0.15
    æ£
    -0.14
    aida
    -0.14
    елÑİ
    -0.14
    ections
    -0.14
    landing
    -0.14
    (primary
    -0.14
     Witt
    -0.14
    POSITIVE LOGITS
    ÑĢава
    0.17
    orca
    0.17
    eware
    0.17
    æĴ°
    0.16
    niÄį
    0.16
    ToProps
    0.16
    amam
    0.15
    è¡
    0.15
    myp
    0.14
    udget
    0.14
    Activations Density 0.053%

    No Known Activations