© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 10915
    Prev
    Next
    INDEX
    Explanations

    references to vehicle specifications and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IU
    -0.15
    æij
    -0.14
     THPT
    -0.14
     Marina
    -0.14
    nel
    -0.14
    Operators
    -0.14
    Ĥ
    -0.13
     flip
    -0.13
    roid
    -0.13
    ucs
    -0.13
    POSITIVE LOGITS
     serial
    0.25
    serial
    0.23
     Serial
    0.23
    Serial
    0.22
     modification
    0.20
    modification
    0.20
     Modification
    0.19
     SERIAL
    0.17
     salon
    0.17
     crossover
    0.17
    Activations Density 0.001%

    No Known Activations