INDEX

Explanations

words related to the Kap community or related names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uated

-0.15

à¹Īà¸£

-0.15

à¤¦à¤°

-0.14

cles

-0.14

tin

-0.14

uates

-0.14

endale

-0.14

amus

-0.14

chter

-0.14

DECL

-0.14

POSITIVE LOGITS

osis

0.19

inos

0.18

à¤¡

0.16

Ð°ÑĢÑĩ

0.16

fen

0.15

usta

0.15

finger

0.15

oho

0.15

etz

0.15

itel

0.14

Activations Density 0.008%

words related to the Kap community or related names

No Comments

No Known Activations