INDEX

Explanations

specific numerical values or identifiers, likely related to dates or statistical data

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

lest

-0.17

_FE

-0.16

 Kirby

-0.14

gaard

-0.14

æ³ķäºº

-0.14

InlineData

-0.14

ceil

-0.14

aid

-0.14

ThanOr

-0.14

ace

-0.14

POSITIVE LOGITS

.scalablytyped

0.18

roc

0.14

_exempt

0.14

çį

0.14

 Breed

0.13

 fanc

0.13

Fuse

0.13

solete

0.13

OTE

0.13

AMES

0.13

Activations Density 0.014%

specific numerical values or identifiers, likely related to dates or statistical data

No Comments

No Known Activations