INDEX

Explanations

phrases indicating denial or refusals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

iasi

-0.15

ÌĨ

-0.15

ddy

-0.15

Ø°

-0.14

:CGRect

-0.14

utherford

-0.14

ibbon

-0.13

andro

-0.13

isible

-0.13

CTest

-0.13

POSITIVE LOGITS

 need

0.54

 must

0.53

 needs

0.50

å¿ħé¡»

0.48

need

0.47

 gotta

0.47

must

0.46

 pháº£i

0.44

 Must

0.44

needs

0.44

Activations Density 0.559%

phrases indicating denial or refusals

No Comments

No Known Activations