© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77520
    Prev
    Next
    INDEX
    Explanations

    terms related to geological layers and rock formations

    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
     Stap
    -0.06
     Indies
    -0.06
    hab
    -0.05
     des
    -0.05
     ok
    -0.05
    æķħ
    -0.05
     ability
    -0.05
    èĺŃ
    -0.05
     div
    -0.05
     Gall
    -0.05
    POSITIVE LOGITS
     layers
    0.09
    òa
    0.09
     layer
    0.09
     ì¸
    0.08
    imator
    0.08
    elay
    0.08
    imson
    0.08
     Beds
    0.08
    alars
    0.08
    SPATH
    0.07
    Activations Density 0.033%

    No Known Activations