© 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. 9-LLAMASCOPE-RES-131K
    11. 95532
    Prev
    Next
    INDEX
    Explanations

    phrases related to leaving or separation

    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
    illo
    -0.08
    odore
    -0.08
    adora
    -0.07
    chin
    -0.07
    parse
    -0.07
    ervo
    -0.07
    ador
    -0.07
    ptr
    -0.07
    empo
    -0.07
    sto
    -0.07
    POSITIVE LOGITS
    ward
    0.10
    ahoo
    0.07
    /loose
    0.07
    etting
    0.07
    /on
    0.07
    ±Ð¾ÑĤ
    0.07
    ICC
    0.07
    icontrol
    0.07
    nings
    0.07
    ikt
    0.07
    Activations Density 0.022%

    No Known Activations