© 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. 17-LLAMASCOPE-RES-131K
    11. 106841
    Prev
    Next
    INDEX
    Explanations

    phrases related to measuring progress and results

    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
    vise
    -0.09
    aga
    -0.07
    seau
    -0.07
     afterwards
    -0.07
    alles
    -0.07
    vat
    -0.07
    ÅĻez
    -0.07
    воз
    -0.07
    998
    -0.07
    FromClass
    -0.06
    POSITIVE LOGITS
     immediate
    0.25
     Immediate
    0.21
    Immediate
    0.18
     immedi
    0.17
     immediately
    0.16
     current
    0.14
     short
    0.13
     sofort
    0.12
     Immediately
    0.12
    current
    0.12
    Activations Density 0.083%

    No Known Activations