INDEX

Explanations

conditional phrases that imply hypothetical situations or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

anes

-0.15

achi

-0.15

ovnÃŃ

-0.14

upe

-0.14

ifice

-0.14

qua

-0.14

atego

-0.14

InRange

-0.13

kou

-0.13

ropolis

-0.13

POSITIVE LOGITS

0.17

 someone

0.15

andel

0.14

hem

0.14

ubar

0.14

_UTF

0.14

åĿĢ

0.14

ahat

0.14

 faced

0.14

 somebody

0.14

Activations Density 0.120%

conditional phrases that imply hypothetical situations or discussions

No Comments

No Known Activations