© 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. 15-LLAMASCOPE-RES-32K
    11. 9127
    Prev
    Next
    INDEX
    Explanations

    discussions related to statistics and proportions concerning specific groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gado
    -0.19
    hol
    -0.17
    iline
    -0.15
     kontakte
    -0.15
    holes
    -0.15
    ιαν
    -0.15
     Stations
    -0.14
    lagen
    -0.14
    andard
    -0.14
    .RegisterType
    -0.14
    POSITIVE LOGITS
     yet
    0.24
    yet
    0.19
     disproportion
    0.18
    åį´
    0.18
     thôi
    0.17
    ãģªãģĮãĤī
    0.17
     (<
    0.16
    Yet
    0.16
     Yet
    0.15
     olsa
    0.15
    Activations Density 0.296%

    No Known Activations