INDEX

Explanations

references to filling or capacity in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ã©c

-0.16

 Freak

-0.15

bom

-0.15

ifica

-0.15

uture

-0.14

qv

-0.14

ais

-0.14

aise

-0.14

isis

-0.14

Bom

-0.13

POSITIVE LOGITS

/full

0.17

ÑĤÐ¸Ð½

0.15

etÃŃ

0.15

-full

0.15

fill

0.15

otion

0.15

_rat

0.14

walls

0.14

 refill

0.14

 empt

0.14

Activations Density 0.069%

references to filling or capacity in various contexts

No Comments

No Known Activations