INDEX

Explanations

expressions of agreement, disapproval, or emotional reactions conveyed through gestures and verbal cues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

itre

-0.18

chez

-0.16

ingers

-0.15

_Att

-0.15

reator

-0.15

Han

-0.14

ampil

-0.14

Att

-0.14

Ĺ

-0.14

ehir

-0.14

POSITIVE LOGITS

 away

0.15

 HARD

0.15

fit

0.15

 vigor

0.15

¨

0.15

åľĪ

0.14

_HARD

0.14

uggest

0.14

lk

0.14

 prof

0.14

Activations Density 0.155%

expressions of agreement, disapproval, or emotional reactions conveyed through gestures and verbal cues

No Comments

No Known Activations