© 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. 8-LLAMASCOPE-RES-32K
    11. 2005
    Prev
    Next
    INDEX
    Explanations

    instances of betrayal or deceit in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cci
    -0.17
    veloper
    -0.17
     Bronze
    -0.16
    chner
    -0.15
    chter
    -0.15
    sez
    -0.15
    ieee
    -0.15
    etti
    -0.14
    eneric
    -0.14
    akeup
    -0.14
    POSITIVE LOGITS
     mainland
    0.15
    913
    0.15
    .codes
    0.14
    town
    0.14
     Edwin
    0.14
    owi
    0.14
     Barber
    0.13
    íĵ¨
    0.13
    ippers
    0.13
     INLINE
    0.13
    Activations Density 0.688%

    No Known Activations