© 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. 93595
    Prev
    Next
    INDEX
    Explanations

    phrases related to crafting and creativity

    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
    ä¸ĸ
    -0.06
    ENTA
    -0.06
     Ga
    -0.06
     brick
    -0.06
     Kom
    -0.06
     pan
    -0.06
     ent
    -0.05
     must
    -0.05
     stew
    -0.05
     soup
    -0.05
    POSITIVE LOGITS
    vál
    0.08
    ÅĤu
    0.08
    å²
    0.07
    ulk
    0.07
    .opendaylight
    0.07
    swing
    0.07
    aben
    0.07
     optionally
    0.07
     addCriterion
    0.07
    éł
    0.07
    Activations Density 0.005%

    No Known Activations