© 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. 2-LLAMASCOPE-RES-32K
    11. 21537
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing work or continuous efforts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLR
    -0.17
    acman
    -0.14
    kening
    -0.14
    Ĺ
    -0.14
     })).
    -0.14
    eous
    -0.13
    rido
    -0.13
    itous
    -0.13
     Canter
    -0.13
    .synthetic
    -0.13
    POSITIVE LOGITS
    ince
    0.23
    aga
    0.18
    uce
    0.16
    talk
    0.16
    ÑĤик
    0.15
    udge
    0.15
    oso
    0.15
    ANE
    0.13
     domin
    0.13
     since
    0.13
    Activations Density 0.281%

    No Known Activations