© 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. 15-LLAMASCOPE-RES-131K
    11. 1031
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and performance standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Forms of the verb "be" (is, are, was, were, been) functioning as auxiliary verbs in predicate constructions, often in technical or explanatory contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     whose
    -0.08
    whose
    -0.08
    ifetime
    -0.07
    ttl
    -0.07
    afa
    -0.06
    olvable
    -0.06
    etu
    -0.06
    elper
    -0.06
    artz
    -0.06
     axe
    -0.06
    POSITIVE LOGITS
    quences
    0.06
    LARI
    0.06
    Ħ
    0.06
    Ł
    0.06
    ATO
    0.06
    pread
    0.06
    PIPE
    0.06
    eland
    0.06
    èª
    0.06
     Kro
    0.06
    Activations Density 0.049%

    No Known Activations