INDEX

Explanations

tasks, actions, or inquiries related to practical exercises and guidance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ãĤīãģĹ

-0.16

FUN

-0.15

CMD

-0.14

deniz

-0.14

ç¬¦

-0.14

 Coordinate

-0.14

seys

-0.14

ibo

-0.14

umes

-0.14

asses

-0.14

POSITIVE LOGITS

ISTA

0.16

 stra

0.16

lÃ¤

0.15

heritance

0.14

LEE

0.14

.onNext

0.14

_warnings

0.13

coming

0.13

ske

0.13

Activations Density 0.061%

tasks, actions, or inquiries related to practical exercises and guidance

No Comments

No Known Activations