INDEX

Explanations

specific terms related to entertainment and media

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uto

-0.16

oves

-0.15

imes

-0.15

procs

-0.15

Ali

-0.14

ëį°

-0.14

otate

-0.14

 è¡ĮæĶ¿

-0.14

 æĭĽ

-0.14

lixir

-0.14

POSITIVE LOGITS

 Harrison

0.15

Ù«

0.14

chap

0.14

uu

0.14

ccione

0.13

estre

0.13

SE

0.13

(?

0.13

Activations Density 0.036%

specific terms related to entertainment and media

No Comments

No Known Activations