INDEX

Explanations

the presence of specific words or phrases indicating a relationship or connection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ì£

-0.16

ÙħÙĦ

-0.16

 çĨ

-0.15

Ø¨Ø§Øª

-0.14

 Guerrero

-0.14

mony

-0.14

="__

-0.14

 Ð¾Ð³ÑĢÐ°

-0.14

tdown

-0.14

POSITIVE LOGITS

0.16

 pass

0.15

 Gauss

0.14

jÃŃ

0.14

aign

0.14

 Ports

0.14

iley

0.14

ihan

0.13

 Jacob

0.13

 Frank

0.13

Activations Density 0.075%

the presence of specific words or phrases indicating a relationship or connection

No Comments

No Known Activations