INDEX

Explanations

references to narrative structure and characters in a story

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ô

-0.16

-0.15

oron

-0.15

illi

-0.14

-DD

-0.14

stamp

-0.14

łí

-0.14

essel

-0.14

iado

-0.13

ordan

-0.13

POSITIVE LOGITS

atrix

0.16

tring

0.15

 ?><?

0.15

opens

0.15

achs

0.15

HING

0.14

 rival

0.14

 inse

0.14

tic

0.13

eba

0.13

Activations Density 0.192%

references to narrative structure and characters in a story

No Comments

No Known Activations