INDEX

Explanations

elements related to measurements and evaluations in research or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ãºt

-0.15

ÄĽtÃŃ

-0.14

unny

-0.14

ToProps

-0.13

onis

-0.13

 PREF

-0.13

 Saves

-0.13

unidad

-0.13

unar

-0.13

 Leban

-0.13

POSITIVE LOGITS

 accumulated

0.18

 Born

0.16

 accumulate

0.15

 resembling

0.15

 piles

0.15

 amassed

0.15

 piled

0.14

 accum

0.14

 born

0.14

 lines

0.14

Activations Density 0.026%

elements related to measurements and evaluations in research or scientific contexts

No Comments

No Known Activations