INDEX

Explanations

words related to manufacturing processes or techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.15

 pivot

-0.15

sei

-0.14

tie

-0.14

 Latter

-0.14

ogan

-0.14

agg

-0.14

 Laud

-0.14

ipse

-0.13

avir

-0.13

POSITIVE LOGITS

_decor

0.17

npos

0.15

anta

0.15

 Fail

0.15

RenderingContext

0.15

SCRI

0.15

SUP

0.14

 ìĿ¸íĦ°ëĦ·

0.14

 Element

0.13

 Postal

0.13

Activations Density 0.000%

words related to manufacturing processes or techniques

No Comments

No Known Activations