INDEX

Explanations

entities, particularly organizations and thematic elements associated with support and community

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

chet

-0.15

acher

-0.15

Ð¾Ð»Ð¶

-0.14

opak

-0.14

kins

-0.14

eza

-0.14

 forth

-0.14

 embassy

-0.14

POSITIVE LOGITS

iou

0.17

NCY

0.17

 jspb

0.16

eras

0.16

flater

0.15

ifndef

0.15

unsch

0.15

ãĥ«ãĤ¯

0.15

ÑĤÐ°Ð±

0.15

ì²Ń

0.14

Activations Density 0.029%

entities, particularly organizations and thematic elements associated with support and community

No Comments

No Known Activations