INDEX

Explanations

mentions of complete or detailed information, particularly in reports or articles

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

urray

-0.15

efe

-0.15

 apolog

-0.15

Hol

-0.15

 hole

-0.14

à¸¡à¸²

-0.13

 major

-0.13

 foss

-0.13

ichel

-0.13

uyu

-0.13

POSITIVE LOGITS

oud

0.16

 details

0.16

/full

0.15

ationship

0.15

-details

0.15

isas

0.14

azers

0.14

_intr

0.14

æ¹

0.14

adata

0.14

Activations Density 0.045%

mentions of complete or detailed information, particularly in reports or articles

No Comments

No Known Activations