INDEX

Explanations

references to locations and their associated attributes or facilitations

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

LOB

-0.16

mrt

-0.15

ective

-0.15

 Arrow

-0.15

Gam

-0.14

Ã©k

-0.14

 reverse

-0.14

áº©n

-0.14

imus

-0.14

ieur

-0.13

POSITIVE LOGITS

adera

0.16

isphere

0.15

 Ãľn

0.14

 GÃ¶z

0.14

ÅĪ

0.14

ÙĬØ¬

0.14

ibar

0.14

_ASSUME

0.14

itage

0.13

ìĶ¨

0.13

Activations Density 0.012%

references to locations and their associated attributes or facilitations

No Comments

No Known Activations