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. 30-LLAMASCOPE-RES-32K
    6. 11100
    Prev
    Next
    INDEX
    Explanations

    details about electrical contracting services

    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
    antaged
    -0.16
    RuntimeObject
    -0.15
    esktop
    -0.15
    ãĥ¼ãĥģ
    -0.15
     rá
    -0.14
    åŃĺäºİ
    -0.14
    velope
    -0.14
    Invariant
    -0.14
    Ñĥнк
    -0.13
     Launcher
    -0.13
    POSITIVE LOGITS
     electrical
    0.55
     Electrical
    0.48
     electric
    0.47
     Electric
    0.42
    Elect
    0.41
     wiring
    0.40
    elect
    0.40
    electric
    0.40
     elect
    0.39
    Electric
    0.39
    Activations Density 0.020%

    No Known Activations