© 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. 87207
    Prev
    Next
    INDEX
    Explanations

    terms related to financial support and accommodation options

    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
    zin
    -0.06
     Pier
    -0.06
    autical
    -0.06
    laus
    -0.06
    ingular
    -0.05
    RAY
    -0.05
    Und
    -0.05
    Äįem
    -0.05
    fram
    -0.05
     Edgar
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĥĦ
    0.07
    HashCode
    0.07
     Army
    0.07
    rin
    0.07
    -Sah
    0.07
    bsp
    0.07
     sustain
    0.07
     morale
    0.07
     Military
    0.07
    ATUS
    0.07
    Activations Density 0.021%

    No Known Activations