INDEX

Explanations

specific names and historical figures

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

incy

-0.16

ndern

-0.14

inaire

-0.14

zion

-0.14

itar

-0.14

ulumi

-0.14

orgia

-0.14

ifax

-0.14

 Congress

-0.13

Insets

-0.13

POSITIVE LOGITS

wick

0.16

ãĥ¼ãĥĭ

0.16

otte

0.16

weit

0.15

 Fetish

0.15

ileged

0.14

iento

0.14

itzer

0.14

irts

0.14

 Lesser

0.14

Activations Density 0.281%

specific names and historical figures

No Known Activations