INDEX

Explanations

expressions related to punishment and aggression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

fel

-0.15

è²»

-0.15

ToStr

-0.15

 Kens

-0.14

ochen

-0.14

 Ladies

-0.14

yn

-0.14

lad

-0.13

POSITIVE LOGITS

_operand

0.18

uger

0.15

Ã¼z

0.15

ìĺģ

0.15

rawer

0.14

ugas

0.14

jez

0.14

 priest

0.14

odom

0.13

utenberg

0.13

Activations Density 0.258%

expressions related to punishment and aggression

No Comments

No Known Activations