© 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. 25-LLAMASCOPE-RES-32K
    11. 22347
    Prev
    Next
    INDEX
    Explanations

    references to events, budgets, and invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.18
     Goodman
    -0.17
     Pok
    -0.17
     speaker
    -0.15
    963
    -0.15
     BUFF
    -0.15
    078
    -0.15
    ula
    -0.15
     parl
    -0.15
     Kore
    -0.14
    POSITIVE LOGITS
     Rounds
    0.17
     lunches
    0.16
    otton
    0.16
    IFS
    0.15
    round
    0.15
    asan
    0.15
    vat
    0.15
     оÑĩ
    0.15
     maduras
    0.15
    iteral
    0.15
    Activations Density 0.012%

    No Known Activations