INDEX

Explanations

words related to components or aspects of machinery or technology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.17

 horse

-0.16

EY

-0.15

plat

-0.14

ude

-0.14

fi

-0.14

es

-0.14

eller

-0.14

lyn

-0.14

POSITIVE LOGITS

HandlerContext

0.15

gre

0.15

 blanks

0.15

ëħ¸ì¶ľ

0.15

orget

0.15

/stretch

0.14

blank

0.14

Leaks

0.14

 NDEBUG

0.14

 Segment

0.14

Activations Density 0.006%

words related to components or aspects of machinery or technology

No Comments

No Known Activations