INDEX

Explanations

phrases that indicate frequency or prevalence of conditions or situations

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

tea

-0.17

phan

-0.16

odem

-0.15

à¸Ńà¸Ļ

-0.15

 Sham

-0.14

egan

-0.14

ray

-0.14

Äģn

-0.14

avl

-0.14

olest

-0.13

POSITIVE LOGITS

 xuyÃªn

0.22

-used

0.20

 occurrence

0.18

ly

0.16

/common

0.16

yny

0.15

 among

0.15

/pop

0.15

 fare

0.15

Activations Density 0.098%

phrases that indicate frequency or prevalence of conditions or situations

No Comments

No Known Activations