© 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. 16144
    Prev
    Next
    INDEX
    Explanations

    names and familial relationships, indicating a focus on lineage and ancestry

    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
     abs
    -0.14
    igham
    -0.14
    ahlen
    -0.14
    asu
    -0.14
    295
    -0.14
    emarks
    -0.13
    aku
    -0.13
     withStyles
    -0.13
     král
    -0.13
     Wander
    -0.13
    POSITIVE LOGITS
     vợ
    0.17
    olute
    0.17
     wife
    0.17
     female
    0.17
     wives
    0.17
     actresses
    0.17
     Female
    0.16
     Lady
    0.16
    _MT
    0.15
     Ther
    0.15
    Activations Density 0.213%

    No Known Activations