© 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. 124949
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal freedom and attachment

    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
    åħ¥ãĤĬ
    -0.08
    alsy
    -0.07
     Born
    -0.06
    _defined
    -0.06
    zac
    -0.06
    ?=
    -0.06
     Nose
    -0.06
    hir
    -0.06
    Born
    -0.05
    ho
    -0.05
    POSITIVE LOGITS
     which
    0.12
    which
    0.10
     that
    0.10
    that
    0.08
     kterou
    0.08
     коÑĤоÑĢÑĭе
    0.08
    Which
    0.08
     Which
    0.07
     WHICH
    0.07
     коÑĤоÑĢÑĥÑİ
    0.07
    Activations Density 0.134%

    No Known Activations