INDEX

Explanations

specific names or significant identifiers in a context related to media or story narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

awl

-0.18

ially

-0.17

als

-0.16

ajÄħ

-0.16

iale

-0.16

Ni

-0.15

Fay

-0.15

adays

-0.15

losure

-0.14

lÃ¡

-0.14

POSITIVE LOGITS

iston

0.16

emoc

0.16

esta

0.15

Ã©ri

0.15

iden

0.15

eri

0.15

uther

0.14

 INTERRUPTION

0.14

esel

0.14

ustos

0.14

Activations Density 0.006%

specific names or significant identifiers in a context related to media or story narratives

No Comments

No Known Activations