INDEX

Explanations

references to filters and cleaning products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

atur

-0.16

aur

-0.15

-0.14

Äįel

-0.14

leep

-0.13

inus

-0.13

 Cowboys

-0.13

 Crossing

-0.13

 calor

-0.13

POSITIVE LOGITS

jabi

0.16

ulong

0.14

acco

0.14

sez

0.14

ogie

0.14

ì§

0.14

ì¡°

0.14

Ø§ÙħÙĦ

0.13

inea

0.13

bet

0.13

Activations Density 0.000%

references to filters and cleaning products

No Comments

No Known Activations