INDEX

Explanations

contextual phrases that indicate location or placement

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

lements

-0.16

-await

-0.15

perate

-0.15

uth

-0.15

annes

-0.14

oord

-0.14

ussion

-0.14

awan

-0.14

utions

-0.14

Mey

-0.14

POSITIVE LOGITS

 Weiner

0.16

ÐµÐ»Ñİ

0.15

elif

0.14

ilio

0.14

lich

0.14

zell

0.14

aff

0.14

 Rubin

0.14

yt

0.14

closing

0.13

Activations Density 0.056%

contextual phrases that indicate location or placement

No Comments

No Known Activations