INDEX

Explanations

phrases indicating ongoing research or current studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Piper

-0.14

Ð¼ÐµÑĩ

-0.14

/GPL

-0.14

 recycl

-0.14

untu

-0.14

nar

-0.13

çĪ¾

-0.13

zas

-0.13

 è»Ĭ

-0.13

BOOLE

-0.13

POSITIVE LOGITS

CLUDING

0.15

Ð»Ð¸ÑĨ

0.14

Å¾ÃŃ

0.14

iked

0.14

_LITERAL

0.14

igham

0.14

cret

0.14

Ply

0.13

idar

0.13

Activations Density 0.019%

phrases indicating ongoing research or current studies

No Comments

No Known Activations