© 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. 27-LLAMASCOPE-RES-32K
    11. 2070
    Prev
    Next
    INDEX
    Explanations

    terms related to applications and registrations in educational or training contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seem
    -0.17
    õi
    -0.15
    ago
    -0.15
    legg
    -0.15
    518
    -0.15
     knew
    -0.14
    ire
    -0.14
    orners
    -0.14
    umba
    -0.14
    ç±į
    -0.14
    POSITIVE LOGITS
     must
    0.24
     cannot
    0.24
     MUST
    0.23
     maybe
    0.22
     does
    0.21
    must
    0.20
    cannot
    0.20
     DOES
    0.19
     Maybe
    0.19
    Maybe
    0.18
    Activations Density 0.351%

    No Known Activations