INDEX

Explanations

instances of the word "detailed."

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

pline

-0.15

 DISPATCH

-0.15

cyl

-0.14

cup

-0.14

 Dillon

-0.14

 batch

-0.14

 crystal

-0.14

entials

-0.13

aine

-0.13

sted

-0.13

POSITIVE LOGITS

leck

0.16

multiline

0.16

ilib

0.15

(IService

0.15

mitt

0.14

atatype

0.14

?action

0.14

æĪ¶

0.14

WithDuration

0.14

ussion

0.14

Activations Density 0.003%

instances of the word "detailed."

No Comments

No Known Activations