INDEX

Explanations

references to URLs and web-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Animalia

-0.14

á»³

-0.14

lew

-0.14

ranÃŃ

-0.14

.Logf

-0.14

ismu

-0.13

áº¹n

-0.13

Gor

-0.13

inded

-0.13

ichel

-0.13

POSITIVE LOGITS

ohl

0.17

ÅĻej

0.16

é¤

0.15

ara

0.15

tain

0.15

spo

0.15

ipar

0.14

ais

0.14

@a

0.14

urm

0.14

Activations Density 0.000%

references to URLs and web-related content

No Comments

No Known Activations