Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95690
    Prev
    Next
    INDEX
    Explanations

    structured data and metadata related to documents or web content

    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
    VR
    -0.06
    attachment
    -0.06
    jang
    -0.06
    ummies
    -0.05
    cores
    -0.05
    uki
    -0.05
    ayo
    -0.05
    اث
    -0.05
    izard
    -0.05
    flower
    -0.05
    POSITIVE LOGITS
    EGIN
    0.07
     bumper
    0.07
    hpp
    0.07
    .AC
    0.06
    agine
    0.06
    Modificar
    0.06
    λά
    0.06
    icina
    0.06
    FRING
    0.06
    lectron
    0.06
    Activations Density 0.022%

    No Known Activations