INDEX

Explanations

phrases related to positive or favorable conditions and situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

_locals

-0.15

enate

-0.15

 McGu

-0.13

ãĥ«ãĥī

-0.13

ogan

-0.13

builtin

-0.13

 AppBundle

-0.13

cent

-0.13

atern

-0.13

 Span

-0.13

POSITIVE LOGITS

 mode

0.17

 state

0.16

 boat

0.15

ocht

0.15

æ¨¡å¼ı

0.15

 ÑģÐ¾ÑģÑĤÐ¾ÑıÐ½Ð¸Ð¸

0.15

inger

0.15

imar

0.15

ymb

0.15

witter

0.15

Activations Density 0.246%

phrases related to positive or favorable conditions and situations

No Comments

No Known Activations