INDEX

Explanations

words associated with discussions or conversations about social or political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ters

-0.15

htub

-0.15

ray

-0.15

Æ¡

-0.14

iers

-0.14

acity

-0.14

rol

-0.14

 Partition

-0.14

ieux

-0.14

hw

-0.14

POSITIVE LOGITS

uso

0.17

å¤ªéĥİ

0.15

asename

0.15

alis

0.15

alach

0.15

ÏģÎ¹Î½

0.14

endid

0.14

WithTag

0.14

ceries

0.14

esi

0.14

Activations Density 0.005%

words associated with discussions or conversations about social or political issues

No Comments

No Known Activations