© 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. 27-LLAMASCOPE-RES-32K
    11. 12066
    Prev
    Next
    INDEX
    Explanations

    numerical data, primarily related to statistics and legal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \grid
    -0.16
    âĢij
    -0.14
    ĥģ
    -0.14
    å¶
    -0.14
    allee
    -0.14
    isors
    -0.14
    zung
    -0.14
    zych
    -0.14
    åĽ£
    -0.14
    achs
    -0.14
    POSITIVE LOGITS
    011
    0.15
    01
    0.15
    tl
    0.15
    010
    0.14
    045
    0.14
    _
    0.14
    621
    0.14
    ’
    0.14
    02
    0.14
    _bullet
    0.14
    Activations Density 0.261%

    No Known Activations