INDEX

Explanations

phrases that express expectations or beliefs about future events

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

aption

-0.16

 addCriterion

-0.15

andle

-0.14

ibox

-0.14

ellig

-0.14

inka

-0.14

 hypothetical

-0.14

Ð´Ð¾Ð¼

-0.14

alim

-0.14

lda

-0.14

POSITIVE LOGITS

ey

0.17

aley

0.15

ÃĹ↵↵

0.14

urge

0.14

Ú¯Ø§Ùĩ

0.14

åĲĽ

0.14

avra

0.13

SV

0.13

*)_

0.13

kel

0.12

Activations Density 0.021%

phrases that express expectations or beliefs about future events

No Comments

No Known Activations