© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87275
    Prev
    Next
    INDEX
    Explanations

    repetitive or comparative language that describes procedures or arguments

    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
    antar
    -0.06
     jer
    -0.06
    jer
    -0.06
    lock
    -0.05
    ENTA
    -0.05
    asco
    -0.05
    us
    -0.05
     Maurit
    -0.05
    udd
    -0.05
    ottie
    -0.05
    POSITIVE LOGITS
    above
    0.11
     except
    0.10
     above
    0.10
    Above
    0.09
    except
    0.09
    Same
    0.08
     same
    0.08
    same
    0.08
     again
    0.08
     Ibid
    0.08
    Activations Density 0.030%

    No Known Activations