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

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 97031
    Prev
    Next
    INDEX
    Explanations

    dialogue or direct quotes within the text

    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
    ãĥĨãĥ«
    -0.08
    erif
    -0.08
    .fields
    -0.08
    iVar
    -0.08
    deaux
    -0.08
     kole
    -0.08
    Ùģس
    -0.07
    	TokenName
    -0.07
    ÅĤu
    -0.07
    еви
    -0.07
    POSITIVE LOGITS
    767
    0.06
    1
    0.06
     ins
    0.05
    igel
    0.05
    ieron
    0.05
     millennia
    0.05
    ym
    0.05
    .
    0.05
    alach
    0.05
     McCoy
    0.05
    Activations Density 0.022%

    No Known Activations