INDEX

Explanations

adjectives associated with cruelty and harshness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

acha

-0.18

á»©ng

-0.17

pany

-0.15

íĨ¡

-0.15

oons

-0.15

.threshold

-0.14

ÅĽnie

-0.14

oub

-0.14

 Kurum

-0.14

POSITIVE LOGITS

 clar

0.15

clr

0.14

*)((

0.14

ãĥªãĤ«

0.14

 rubber

0.14

æ¨Ļ

0.14

atest

0.13

 Rubber

0.13

 alarm

0.13

Activations Density 0.005%

adjectives associated with cruelty and harshness

No Comments

No Known Activations