INDEX

Explanations

elements of narrative structure

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

oto

-0.16

ozo

-0.16

toi

-0.15

åĪļæīį

-0.15

Ã¤nn

-0.14

lds

-0.14

addon

-0.14

onaut

-0.14

ales

-0.14

elson

-0.14

POSITIVE LOGITS

bane

0.16

ÑĢÑıÐ´Ñĥ

0.16

unb

0.15

 among

0.15

ync

0.15

among

0.15

 guess

0.14

 amongst

0.14

 Accom

0.14

 Guess

0.14

Activations Density 0.180%

elements of narrative structure

No Comments

No Known Activations