Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 16112
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and policy issues

    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
    oggler
    -0.15
    ouncer
    -0.15
    apeutics
    -0.14
    ansas
    -0.14
    bero
    -0.13
    rastructure
    -0.13
    aviour
    -0.13
    Ïģε
    -0.13
    fortunate
    -0.13
    igsaw
    -0.13
    POSITIVE LOGITS
    uably
    0.19
    etheless
    0.19
    ecause
    0.17
    sequently
    0.16
    itionally
    0.15
    pecially
    0.15
    theless
    0.14
    inally
    0.14
    fully
    0.14
    umably
    0.13
    Activations Density 0.583%

    No Known Activations