INDEX

Explanations

references to accessories

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

soever

-0.19

stile

-0.18

rrha

-0.17

æ¶

-0.15

ÑĢÑĥÑĤ

-0.14

ska

-0.14

 Predictor

-0.14

(er

-0.13

kker

-0.13

POSITIVE LOGITS

bright

0.14

yonel

0.14

ENA

0.13

ãĤ·ãĥ§ãĥ³

0.13

cete

0.13

izons

0.13

vertime

0.13

rouch

0.13

è³ª

0.13

Activations Density 0.013%

references to accessories

No Comments

No Known Activations