INDEX

Explanations

references that indicate locations or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

;element

-0.16

ÙĭØ§

-0.15

aad

-0.15

)((((

-0.15

ÑĬ

-0.15

isko

-0.14

aylight

-0.14

Ĥ

-0.14

¤

-0.14

awn

-0.14

POSITIVE LOGITS

 cover

0.16

abis

0.16

SB

0.16

çĿ

0.15

 impro

0.15

dur

0.15

asl

0.15

longleftrightarrow

0.15

kie

0.14

ÃŃme

0.14

Activations Density 0.106%

references that indicate locations or positions

No Comments

No Known Activations