INDEX

Explanations

phrases related to destruction or harmful actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

iras

-0.18

esta

-0.17

.truth

-0.15

atal

-0.15

oom

-0.14

 trá»Ŀi

-0.14

cot

-0.14

 turb

-0.14

esar

-0.14

elier

-0.14

POSITIVE LOGITS

urgeon

0.16

essel

0.16

pta

0.15

vÄĽd

0.15

ienne

0.15

FileVersion

0.15

 Lambert

0.14

zent

0.14

spb

0.14

 RegexOptions

0.13

Activations Density 0.026%

phrases related to destruction or harmful actions

No Comments

No Known Activations