Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 16490
    Prev
    Next
    INDEX
    Explanations

    relationships between tables in a database

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieber
    -0.15
    ÙĬاÙĨ
    -0.15
    QUIRE
    -0.14
    .none
    -0.14
    lsa
    -0.14
    onder
    -0.13
    duit
    -0.13
    ovalo
    -0.13
    TypeInfo
    -0.13
    raft
    -0.13
    POSITIVE LOGITS
    fk
    0.19
     EXISTS
    0.18
    `.`
    0.18
     FK
    0.18
    .*,
    0.17
     CAST
    0.17
     fk
    0.16
    _fk
    0.16
     cast
    0.16
    PK
    0.16
    Activations Density 0.024%

    No Known Activations