© 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. 76150
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" typically indicating the presence of something

    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
    sla
    -0.06
    sburg
    -0.06
     decentral
    -0.06
    NibName
    -0.06
    trak
    -0.06
    urm
    -0.06
    hari
    -0.06
    anou
    -0.06
    >NN
    -0.05
     dop
    -0.05
    POSITIVE LOGITS
    ánh
    0.07
    curities
    0.07
    /pub
    0.07
    ethod
    0.07
    agation
    0.07
    otime
    0.07
    erval
    0.06
     writeTo
    0.06
    arus
    0.06
    abcdefghijklmnop
    0.06
    Activations Density 0.010%

    No Known Activations