© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129957
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conjunctions

    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
    usz
    -0.07
    ãĥ¼ãĥ³
    -0.07
    GLOSS
    -0.06
    aison
    -0.06
    kat
    -0.06
    Absent
    -0.06
    icina
    -0.06
    aki
    -0.05
    Īĺ
    -0.05
    assin
    -0.05
    POSITIVE LOGITS
    HEMA
    0.08
    istrovstvÃŃ
    0.07
     tre
    0.07
    lacak
    0.07
    ategory
    0.07
    ovich
    0.07
    izr
    0.07
    NewProp
    0.07
    iser
    0.07
    eson
    0.07
    Activations Density 0.000%

    No Known Activations