INDEX

Explanations

expressions of doubt or uncertainty regarding beliefs and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

toc

-0.16

liers

-0.14

SizeMode

-0.14

gary

-0.14

 fraction

-0.14

Fraction

-0.13

 Fraction

-0.13

éº¦

-0.13

 Alma

-0.13

fug

-0.13

POSITIVE LOGITS

andon

0.18

 necessarily

0.17

onaut

0.15

celik

0.15

_FA

0.15

inden

0.14

Ð±Ñĭ

0.14

undy

0.14

opsy

0.14

antha

0.14

Activations Density 0.170%

expressions of doubt or uncertainty regarding beliefs and opinions

No Comments

No Known Activations