INDEX

Explanations

concepts related to teaching and the sharing of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Verdana

-0.17

TRACT

-0.16

 Muham

-0.15

ìĽĥ

-0.14

-Sah

-0.14

 Perr

-0.14

ÙĦÙħÙĩ

-0.14

 Grove

-0.14

 Picks

-0.14

RITE

-0.14

POSITIVE LOGITS

obl

0.14

 Townsend

0.14

 represented

0.14

ÄĻd

0.14

zas

0.14

 delivery

0.13

umo

0.13

umont

0.13

Lud

0.13

 mixed

0.13

Activations Density 0.035%

concepts related to teaching and the sharing of knowledge

No Comments

No Known Activations