INDEX

Explanations

mentions of appearances and participation in media or events

oai_token-act-pair · gpt-4o-mini

Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 consum

-0.15

å¾©

-0.14

fast

-0.13

plex

-0.13

 Feast

-0.13

ÐµÑĢÐ¾Ð²

-0.13

acus

-0.13

 fast

-0.13

upo

-0.13

POSITIVE LOGITS

 alongside

0.27

 twice

0.20

along

0.20

 opposite

0.19

 together

0.18

 Twice

0.16

 along

0.15

ategories

0.15

 briefly

0.15

aku

0.15

Activations Density 0.117%

mentions of appearances and participation in media or events

No Known Activations