INDEX

Explanations

occurrences of proper nouns, particularly names and locations related to current events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

/bower

-0.17

acimiento

-0.16

Ð¼ÑĸÐ½Ñĸ

-0.16

_TD

-0.15

 Desk

-0.15

-0.14

rana

-0.14

á»«a

-0.14

ç»Ī

-0.14

 Weinstein

-0.14

POSITIVE LOGITS

 Lewis

0.18

 Reuters

0.16

 alter

0.16

ÐµÐ»Ð¸Ðº

0.14

pus

0.14

 Alter

0.14

_SKIP

0.14

 succ

0.14

 centr

0.14

 earlier

0.14

Activations Density 0.006%

occurrences of proper nouns, particularly names and locations related to current events

No Comments

No Known Activations