© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126592
    Prev
    Next
    INDEX
    Explanations

    the presence of non-English characters or encoding issues

    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
    ersist
    -0.08
    andes
    -0.07
    nos
    -0.07
    yr
    -0.07
    onde
    -0.07
    etta
    -0.06
    852
    -0.06
    ÌĢ
    -0.06
    alog
    -0.06
     gun
    -0.06
    POSITIVE LOGITS
    bigint
    0.06
    icho
    0.06
    елÑİ
    0.06
    .head
    0.06
    еÑĩ
    0.06
    ear
    0.06
     Clan
    0.06
    itor
    0.06
    WithIdentifier
    0.06
     Klein
    0.06
    Activations Density 0.000%

    No Known Activations