© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16169
    Prev
    Next
    INDEX
    Explanations

    references to online gaming and gambling communities

    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
    @d
    -0.06
    usat
    -0.06
     Byl
    -0.06
    ãĥ¼ãĥ³
    -0.06
     Bound
    -0.06
    mina
    -0.06
     kdo
    -0.06
     VÅ¡
    -0.06
    anh
    -0.06
    zend
    -0.06
    POSITIVE LOGITS
    785
    0.06
    .Atomic
    0.06
    uncture
    0.06
    sembly
    0.06
    BackingField
    0.06
    .ManyToMany
    0.06
     surround
    0.06
    aison
    0.06
    295
    0.06
    -valu
    0.06
    Activations Density 0.016%

    No Known Activations