© 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. 126442
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this," indicating a focus on immediacy or particular references

    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
     вÑģÑĤ
    -0.07
    код
    -0.06
    esson
    -0.06
     Zd
    -0.06
    ious
    -0.06
    _OW
    -0.06
    BuilderFactory
    -0.06
    culus
    -0.06
     Autonomous
    -0.06
    inou
    -0.06
    POSITIVE LOGITS
    conditionally
    0.06
    eway
    0.06
    ullan
    0.06
    istically
    0.06
    sing
    0.06
    lant
    0.06
    tl
    0.06
    tar
    0.06
    ologically
    0.06
    548
    0.06
    Activations Density 0.026%

    No Known Activations