© 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. 126262
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events

    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
    omik
    -0.09
    StackNavigator
    -0.08
    AdapterFactory
    -0.08
    bruary
    -0.07
    ccione
    -0.07
    asher
    -0.07
    RuntimeObject
    -0.07
    rrha
    -0.07
    _mE
    -0.07
    BOOLE
    -0.07
    POSITIVE LOGITS
    quot
    0.06
     Kelvin
    0.06
     bl
    0.06
    Ãł
    0.06
     Undefined
    0.06
    éĴŁ
    0.06
    _TP
    0.06
     Ja
    0.06
    ãĤĵãģ¨
    0.06
    ager
    0.06
    Activations Density 0.080%

    No Known Activations