© 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. 18-LLAMASCOPE-RES-32K
    11. 5934
    Prev
    Next
    INDEX
    Explanations

    words related to denial or rejection of serious allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramer
    -0.16
     Danh
    -0.15
     svém
    -0.14
    ungle
    -0.14
    .owl
    -0.14
    tant
    -0.13
    ÑĨеп
    -0.13
    imson
    -0.13
    ffset
    -0.13
    ialect
    -0.13
    POSITIVE LOGITS
     fact
    0.31
     manner
    0.25
    fact
    0.23
     amount
    0.21
     tendency
    0.20
     role
    0.19
     way
    0.18
     importance
    0.17
     impact
    0.16
     recent
    0.16
    Activations Density 0.258%

    No Known Activations