Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43879
    Prev
    Next
    INDEX
    Explanations

    references to services and actions related to moving and relocation

    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
     FIN
    -0.06
    aci
    -0.06
    oney
    -0.06
     Carm
    -0.05
     finance
    -0.05
    åĺī
    -0.05
    yang
    -0.05
    finance
    -0.05
    kr
    -0.05
    -ser
    -0.05
    POSITIVE LOGITS
     very
    0.15
     own
    0.13
     really
    0.12
     marginal
    0.11
     early
    0.10
    Very
    0.10
     exact
    0.10
     très
    0.10
     necessary
    0.09
     rất
    0.09
    Activations Density 0.004%

    No Known Activations