INDEX

Explanations

terms related to structured formats or components in various contexts

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

arer

-0.17

etik

-0.16

eri

-0.15

anan

-0.14

IRM

-0.14

anh

-0.14

etcode

-0.14

 ÑģÑħ

-0.14

çıł

-0.14

idla

-0.13

POSITIVE LOGITS

cep

0.18

-long

0.15

icipant

0.15

swith

0.15

ivar

0.14

ongo

0.14

-strong

0.14

aur

0.14

 indictment

0.14

rong

0.13

Activations Density 0.126%

terms related to structured formats or components in various contexts

No Comments

No Known Activations