© 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. 11384
    Prev
    Next
    INDEX
    Explanations

    sequences related to data submission and availability in research contexts

    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
     trim
    -0.15
     ramp
    -0.15
    umberland
    -0.14
    å©ļ
    -0.14
     agenda
    -0.14
     Century
    -0.14
    256
    -0.13
    rar
    -0.13
     Agenda
    -0.13
     ÑĢа
    -0.13
    POSITIVE LOGITS
    .ncbi
    0.20
     NC
    0.19
    .nlm
    0.18
    HG
    0.18
    ebi
    0.18
    _MOUSE
    0.18
    NC
    0.18
     curator
    0.17
     Ent
    0.17
     Swiss
    0.17
    Activations Density 0.067%

    No Known Activations