INDEX

Explanations

navigation-related elements such as sections and links

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

stal

-0.16

cale

-0.14

oper

-0.13

wers

-0.13

->↵

-0.13

ÐµÑī

-0.13

_CF

-0.13

oa

-0.13

ometer

-0.13

POSITIVE LOGITS

hend

0.15

 herk

0.14

ROKE

0.14

 Brill

0.14

evi

0.14

ãĥ¼ãĥĵ

0.13

TYPO

0.13

ogne

0.13

IBUT

0.13

Activations Density 0.012%

navigation-related elements such as sections and links

No Comments

No Known Activations