INDEX

Explanations

references to definitions and explanations of terms or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

eros

-0.16

erot

-0.16

faction

-0.15

  ↵  ↵

-0.15

fac

-0.15

beiter

-0.14

Ð¶ÐµÐ½

-0.14

fork

-0.14

AtPath

-0.14

factory

-0.14

POSITIVE LOGITS

initely

0.23

nable

0.20

-def

0.18

Def

0.18

unkt

0.18

azio

0.17

iciency

0.16

.Def

0.16

ining

0.16

 bomb

0.16

Activations Density 0.033%

references to definitions and explanations of terms or concepts

No Comments

No Known Activations