© 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. 15-LLAMASCOPE-RES-131K
    6. 90307
    Prev
    Next
    INDEX
    Explanations

    mentions of durations or time frames

    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
    wald
    -0.08
    recent
    -0.07
    nts
    -0.07
    odata
    -0.07
     Seit
    -0.07
    اÙĨس
    -0.07
    ettel
    -0.07
    Ctl
    -0.06
    erner
    -0.06
    STA
    -0.06
    POSITIVE LOGITS
     until
    0.07
    ignon
    0.06
    cury
    0.06
     weitere
    0.06
     years
    0.06
    Quote
    0.06
    Remaining
    0.06
    470
    0.06
    iley
    0.06
     Until
    0.06
    Activations Density 0.014%

    No Known Activations