INDEX

Explanations

terms related to requests and administrative operations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

stav

-0.15

_UNDEF

-0.15

ÑıÑĤ

-0.15

loha

-0.14

tl

-0.14

 BorderRadius

-0.14

ActivityResult

-0.14

Jar

-0.14

elligent

-0.13

Jar

-0.13

POSITIVE LOGITS

 Seks

0.17

pla

0.16

issen

0.16

endcode

0.16

hg

0.15

ibre

0.14

_TUN

0.14

Sne

0.14

ocity

0.14

 Clamp

0.14

Activations Density 0.007%

terms related to requests and administrative operations

No Comments

No Known Activations