© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77456
    Prev
    Next
    INDEX
    Explanations

    the presence of specific pronouns indicating possession or association

    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
    ffset
    -0.08
    -------------</
    -0.08
    ontent
    -0.08
     ogl
    -0.08
    éĴ®
    -0.08
     authDomain
    -0.08
    ieur
    -0.08
    culus
    -0.08
    IRR
    -0.08
    ısıt
    -0.07
    POSITIVE LOGITS
    got
    0.06
     sooner
    0.06
     and
    0.05
    ,
    0.05
    .jpeg
    0.05
     got
    0.05
    's
    0.05
     
    0.05
    ¾
    0.05
     solely
    0.05
    Activations Density 0.000%

    No Known Activations