INDEX

Explanations

numerical representations related to time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

phies

-0.15

-0.14

GGLE

-0.14

Dah

-0.14

-0.13

ulton

-0.13

elp

-0.13

panion

-0.13

POSITIVE LOGITS

wiÄħ

0.15

Ð¾ÑĤÑĢÐµÐ±

0.13

ighet

0.13

pmat

0.13

quin

0.13

.ps

0.13

uyá»ĩn

0.13

\admin

0.13

(Target

0.13

amination

0.13

Activations Density 0.021%

numerical representations related to time

No Comments

No Known Activations