© 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. 75259
    Prev
    Next
    INDEX
    Explanations

    numerical data, primarily associated with geographic or temporal 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
    ssize
    -0.07
    Ùį
    -0.06
    asher
    -0.06
    ]={↵
    -0.06
    Nie
    -0.06
     Nej
    -0.06
    ptype
    -0.06
    ojis
    -0.06
    izr
    -0.06
    ÙĪÙĬÙĥ
    -0.06
    POSITIVE LOGITS
    200
    0.23
    Û²Û°Û°
    0.12
    201
    0.10
    199
    0.09
    202
    0.08
    197
    0.08
    190
    0.07
    oÅĪ
    0.07
    ®
    0.07
     Bush
    0.07
    Activations Density 0.056%

    No Known Activations