INDEX

Explanations

words that indicate a state of being or positional descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ien

-0.16

bers

-0.16

ign

-0.14

Î¸Î®

-0.14

llib

-0.14

ters

-0.14

 RaisePropertyChanged

-0.14

inq

-0.13

rys

-0.13

 cellul

-0.13

POSITIVE LOGITS

cum

0.14

ogn

0.14

avec

0.14

dice

0.13

orre

0.13

.cz

0.13

Ã¡na

0.13

 ØµØ¯

0.13

.isNullOrEmpty

0.13

Ð°Ð½Ð°

0.13

Activations Density 0.017%

words that indicate a state of being or positional descriptors

No Comments

No Known Activations