© 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. 30-LLAMASCOPE-RES-32K
    11. 17343
    Prev
    Next
    INDEX
    Explanations

    instances of quotes and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umper
    -0.15
    ingo
    -0.15
    Ïģοι
    -0.15
    'hui
    -0.14
     defaultMessage
    -0.14
     yyn
    -0.14
    ç¿°
    -0.14
    'na
    -0.14
    gst
    -0.13
    ories
    -0.13
    POSITIVE LOGITS
    ve
    0.39
    ll
    0.37
     ve
    0.32
     ll
    0.29
    LL
    0.27
    re
    0.26
    VE
    0.26
    d
    0.24
    .ll
    0.23
    _ll
    0.23
    Activations Density 0.016%

    No Known Activations