INDEX

Explanations

phrases related to personal responsibility and accountability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

urat

-0.16

rowave

-0.16

ÐļÐĺ

-0.15

iscal

-0.15

innen

-0.15

iÅ¾

-0.15

utton

-0.15

Foo

-0.14

 Mint

-0.14

gow

-0.14

POSITIVE LOGITS

 else

0.17

bud

0.15

 otherwise

0.15

avou

0.15

0.14

 à¤Ĩà¤§

0.14

bef

0.14

det

0.14

 risks

0.14

Activations Density 0.126%

phrases related to personal responsibility and accountability

No Comments

No Known Activations