INDEX

Explanations

references to specific editions or releases of products or media

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

eon

-0.19

ãģªãĤĭ

-0.18

er

-0.15

ans

-0.15

ff

-0.15

feld

-0.14

anja

-0.14

let

-0.14

iet

-0.14

lett

-0.14

POSITIVE LOGITS

TS

0.17

ckeditor

0.16

caÃ§Ã£o

0.15

redient

0.15

ãĤ¿ãĤ¤

0.15

holm

0.15

à¸¥

0.14

roit

0.14

izione

0.14

rics

0.14

Activations Density 0.016%

references to specific editions or releases of products or media

No Comments

No Known Activations

references to specific editions or releases of products or media

No Comments

No Known Activations