© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to counseling and therapy

    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
    esel
    -0.08
    ummings
    -0.07
    achi
    -0.07
    wall
    -0.07
    kem
    -0.07
    ensus
    -0.07
    acl
    -0.07
    bol
    -0.07
    -wall
    -0.07
    lili
    -0.07
    POSITIVE LOGITS
    led
    0.08
    ogue
    0.06
    ear
    0.06
    ings
    0.06
    ship
    0.06
    nder
    0.06
    -NLS
    0.06
    patibility
    0.06
    Ñīик
    0.06
    огод
    0.06
    Activations Density 0.010%

    No Known Activations