INDEX

Explanations

terms related to review ratings and aggregation sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ainen

-0.16

erce

-0.15

ÃŃo

-0.15

 Gazette

-0.15

ooter

-0.15

roud

-0.14

 à¤¬à¤²

-0.14

 competitive

-0.14

ERA

-0.13

cestor

-0.13

POSITIVE LOGITS

ÙģÙĩÙĪÙħ

0.14

é¡µéĿ¢åŃĺæ¡£å¤ĩä»½

0.14

ubern

0.14

hev

0.14

_patch

0.14

Callable

0.13

ipur

0.13

 downtown

0.13

 getNode

0.13

 treff

0.13

Activations Density 0.011%

terms related to review ratings and aggregation sources

No Comments

No Known Activations