INDEX

Explanations

expressions of personal opinion and subjective experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

allee

-0.15

appen

-0.15

UME

-0.15

.easing

-0.15

 McMahon

-0.15

ebi

-0.14

ume

-0.14

ith

-0.14

geme

-0.14

agnet

-0.14

POSITIVE LOGITS

 personally

0.20

 Personally

0.20

Personally

0.16

 myself

0.15

iyim

0.15

hoff

0.15

gef

0.14

 pict

0.14

 prefer

0.14

¹Ħ

0.14

Activations Density 0.044%

expressions of personal opinion and subjective experiences

No Comments

No Known Activations