© 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. 23-LLAMASCOPE-RES-32K
    11. 27959
    Prev
    Next
    INDEX
    Explanations

    sentences focused on personal experiences and expressions of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruta
    -0.15
    MBER
    -0.14
    ertino
    -0.14
    Dll
    -0.14
    lk
    -0.14
    routes
    -0.14
    Ñĥва
    -0.13
     Bulk
    -0.13
    avax
    -0.13
    prox
    -0.13
    POSITIVE LOGITS
    aved
    0.19
     tanto
    0.18
     encounter
    0.18
    aves
    0.17
     encounters
    0.16
     æīĢ
    0.16
     Encounter
    0.16
    ivate
    0.15
    ÏĢο
    0.15
    bservice
    0.15
    Activations Density 0.235%

    No Known Activations