INDEX

Explanations

phrases that introduce or emphasize a concept or idea

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

owi

-0.18

Fi

-0.16

ous

-0.14

ÑĢÐ°Ñħ

-0.14

ektor

-0.14

ric

-0.14

velle

-0.13

ognito

-0.13

POSITIVE LOGITS

afen

0.18

ilden

0.17

\Carbon

0.14

uger

0.14

preg

0.14

anni

0.14

idelity

0.14

orrent

0.14

PIPE

0.14

urgeon

0.14

Activations Density 0.049%

phrases that introduce or emphasize a concept or idea

No Comments

No Known Activations