© 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. 17-LLAMASCOPE-RES-131K
    6. 29626
    Prev
    Next
    INDEX
    Explanations

    grammatical artifacts and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A period immediately followed by double angle brackets that typically indicates the end of a section, paragraph, or list item, often followed by a new section beginning on the next line.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    onom
    -0.06
    #a
    -0.06
    ello
    -0.06
    ecess
    -0.06
    HTTPRequest
    -0.06
     hum
    -0.06
    ampo
    -0.06
     Redistributions
    -0.05
    _SECURITY
    -0.05
    lenmiÅŁ
    -0.05
    POSITIVE LOGITS
    iculty
    0.06
    opa
    0.06
    iem
    0.06
    orestation
    0.06
     Cunning
    0.06
     whereas
    0.06
    awks
    0.06
    ols
    0.06
    ersen
    0.06
    ork
    0.06
    Activations Density 0.060%

    No Known Activations