© 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. 90440
    Prev
    Next
    INDEX
    Explanations

    repeated punctuation marks, particularly periods and semicolons

    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
    roach
    -0.08
    IVA
    -0.07
    ameleon
    -0.07
    anken
    -0.07
    akens
    -0.07
     tÅĻeba
    -0.07
    assed
    -0.07
    LIK
    -0.07
    utherford
    -0.07
    grav
    -0.07
    POSITIVE LOGITS
     this
    0.07
    ört
    0.07
     thus
    0.06
     This
    0.06
     Erg
    0.06
     ponder
    0.06
     fim
    0.06
     Thus
    0.06
     Wa
    0.06
    ghan
    0.06
    Activations Density 0.007%

    No Known Activations