INDEX

Explanations

technical terms related to data analysis and feature extraction in computational contexts

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

ermen

-0.16

NL

-0.15

town

-0.15

asco

-0.15

cka

-0.15

ier

-0.14

idy

-0.14

ìĭ±

-0.14

imer

-0.14

utor

-0.14

POSITIVE LOGITS

arth

0.16

isman

0.15

interop

0.15

_MISC

0.14

orial

0.14

MethodInfo

0.14

yme

0.13

-pres

0.13

 Cres

0.13

_AC

0.13

Activations Density 0.014%

technical terms related to data analysis and feature extraction in computational contexts

No Comments

No Known Activations