INDEX

Explanations

first-person pronouns, indicating personal perspective or experience

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

reeze

-0.18

eyse

-0.15

urga

-0.15

AffineTransform

-0.15

itol

-0.14

chwitz

-0.14

eÅŁ

-0.14

 rÃ¡m

-0.14

CommandEvent

-0.14

udget

-0.14

POSITIVE LOGITS

acs

0.16

ofs

0.15

0.14

à¤¹à¤¨

0.14

pau

0.14

in

0.14

ica

0.14

so

0.13

reset

0.13

Activations Density 0.086%

first-person pronouns, indicating personal perspective or experience

No Comments

No Known Activations