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. 44068
    Prev
    Next
    INDEX
    Explanations

    compound words and phrases suggesting togetherness or partnership

    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
    tor
    -0.08
    bic
    -0.08
    ULSE
    -0.08
    arcy
    -0.07
    ts
    -0.07
    lice
    -0.07
    ular
    -0.07
    tiv
    -0.07
    tv
    -0.07
    loid
    -0.07
    POSITIVE LOGITS
    gether
    0.22
     together
    0.17
     Together
    0.15
    Together
    0.14
    ether
    0.14
    get
    0.13
    ther
    0.12
     gather
    0.11
    ä¸Ģèµ·
    0.11
     gathers
    0.10
    Activations Density 0.005%

    No Known Activations