© 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. 24-LLAMASCOPE-RES-32K
    11. 5725
    Prev
    Next
    INDEX
    Explanations

    terms related to the usage and sharing of personal information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     using
    -0.35
    using
    -0.34
    -using
    -0.33
     used
    -0.31
     Using
    -0.31
    _USED
    -0.30
     Used
    -0.30
    Using
    -0.30
     USING
    -0.29
    -used
    -0.29
    POSITIVE LOGITS
     abuse
    0.23
     abused
    0.20
     Abuse
    0.18
     misuse
    0.17
     mis
    0.17
     abuses
    0.16
    age
    0.16
     Juice
    0.15
     employ
    0.15
     Mis
    0.15
    Activations Density 0.064%

    No Known Activations