INDEX

Explanations

references to relationships and interactions between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

roma

-0.17

aur

-0.16

ç¾½

-0.15

ibt

-0.15

Ø®Ø´

-0.15

ustin

-0.15

ouch

-0.15

ORMAT

-0.14

omor

-0.14

uyo

-0.14

POSITIVE LOGITS

otec

0.16

REAM

0.15

oje

0.15

itted

0.15

 Minority

0.14

_vid

0.14

enthal

0.14

 Pazar

0.14

AdapterFactory

0.14

_OW

0.14

Activations Density 0.324%

references to relationships and interactions between characters

No Comments

No Known Activations