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. 17914
    Prev
    Next
    INDEX
    Explanations

    references to institutions, roles, or positions related to information and assistance

    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
    Tau
    -0.21
     Trit
    -0.19
    tid
    -0.19
    _tid
    -0.18
     Tau
    -0.17
    tar
    -0.17
    Terminal
    -0.16
    esin
    -0.16
    _tunnel
    -0.16
    ниÑĩ
    -0.16
    POSITIVE LOGITS
     tom
    1.13
     Tom
    1.10
    Tom
    1.02
     TOM
    0.98
    tom
    0.92
     Том
    0.91
     Thomas
    0.90
     tomato
    0.85
    .tom
    0.85
     tomatoes
    0.84
    Activations Density 0.046%

    No Known Activations