INDEX

Explanations

expressions of uncertainty or rhetorical questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

dy

-0.17

osis

-0.17

iani

-0.16

elia

-0.15

anh

-0.15

ortex

-0.15

gba

-0.15

pector

-0.14

Dy

-0.14

chw

-0.14

POSITIVE LOGITS

0.16

 vanity

0.15

Î¹Î±Î½

0.15

reon

0.15

iddet

0.15

WebResponse

0.14

chie

0.14

 being

0.14

à¸¡à¸Ļ

0.14

 besides

0.14

Activations Density 0.004%

expressions of uncertainty or rhetorical questions

No Comments

No Known Activations