© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61159
    Prev
    Next
    INDEX
    Explanations

    references to "cross" or related terms in various contexts

    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
    iko
    -0.08
    ertas
    -0.08
    ÏħÏĥ
    -0.07
    ernals
    -0.07
    ocene
    -0.07
    /rfc
    -0.07
    .opendaylight
    -0.07
    пеÑĩ
    -0.07
    ardo
    -0.07
    KO
    -0.07
    POSITIVE LOGITS
     cross
    0.13
     Cross
    0.11
    -cross
    0.11
    cross
    0.10
    Cross
    0.10
    .cross
    0.10
    .Cross
    0.09
    roads
    0.09
    aint
    0.08
     CROSS
    0.08
    Activations Density 0.016%

    No Known Activations