Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29067
    Prev
    Next
    INDEX
    Explanations

    instances of the word "search" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    its
    -0.07
    gel
    -0.06
    иÑĨ
    -0.06
    ema
    -0.06
    329
    -0.06
     Proud
    -0.06
     Err
    -0.06
    gest
    -0.06
    akens
    -0.06
    bler
    -0.06
    POSITIVE LOGITS
    หาร
    0.08
    viso
    0.07
    mtree
    0.07
    enet
    0.07
    лÑıÑħ
    0.07
    (search
    0.06
    idis
    0.06
    iglia
    0.06
    kus
    0.06
    éf
    0.06
    Activations Density 0.001%

    No Known Activations