INDEX

Explanations

hyphens and related formatting elements used in coding and technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

acre

-0.16

ÑģÑĤÐ¸

-0.15

zag

-0.15

yal

-0.15

 word

-0.14

iagnostics

-0.14

 analogy

-0.14

kor

-0.14

ypse

-0.14

lo

-0.14

POSITIVE LOGITS

ojÃŃ

0.16

ISTA

0.15

å¹²

0.15

idl

0.15

uther

0.14

icode

0.14

etty

0.14

Î½Îµ

0.14

htable

0.14

ACA

0.14

Activations Density 0.013%

hyphens and related formatting elements used in coding and technical documentation

No Comments

No Known Activations