INDEX

Explanations

comments and annotations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Hack

-0.16

lÃ½

-0.15

reed

-0.15

imestone

-0.15

kinson

-0.15

abo

-0.14

Ð¾Ð¶Ðµ

-0.14

à¤¿à¤¶à¤¤

-0.14

Ð¾Ð±ÑĢÐ°Ð·

-0.14

 Gast

-0.13

POSITIVE LOGITS

utilus

0.16

ensis

0.14

arakter

0.14

 ÑģÐµÐ±

0.14

olik

0.13

etsk

0.13

ÏĥÎ·

0.13

ote

0.13

itch

0.13

 onCreateViewHolder

0.13

Activations Density 0.014%

comments and annotations in code

No Comments

No Known Activations