© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15708
    Prev
    Next
    INDEX
    Explanations

    references to the word "anchor" and its variations

    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
    ofday
    -0.09
    eel
    -0.08
    oksen
    -0.08
    oleon
    -0.08
    arus
    -0.08
    oil
    -0.07
    ofire
    -0.07
    qv
    -0.07
    ASH
    -0.07
    aris
    -0.07
    POSITIVE LOGITS
    ãĥ§
    0.10
    (es
    0.10
    á»ĵng
    0.10
    à¥įà¤ļ
    0.09
    à¥įà¤Ľ
    0.09
    midt
    0.08
    ttp
    0.08
    etta
    0.08
    es
    0.07
    mate
    0.07
    Activations Density 0.045%

    No Known Activations