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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95952
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating superiority or preference

    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
    gaard
    -0.08
    rah
    -0.08
    isp
    -0.07
    adlo
    -0.07
    SSIP
    -0.07
    cult
    -0.07
    èles
    -0.07
    prit
    -0.07
    elong
    -0.07
    sWith
    -0.07
    POSITIVE LOGITS
    'gc
    0.07
    ãģĬãĤĬ
    0.07
    aja
    0.06
    ipur
    0.06
     ifndef
    0.06
     those
    0.06
    ifold
    0.06
    ê»ĺ
    0.06
    åļ
    0.06
    olic
    0.06
    Activations Density 0.017%

    No Known Activations