INDEX

Explanations

specific names or references related to individuals or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

badge

-0.15

importe

-0.14

ë¶Ģ

-0.14

Minimal

-0.14

ÑĤÑĮ

-0.13

adin

-0.13

ãĥĸãĥ«

-0.13

ì¦Ŀ

-0.13

pe

-0.13

ĨĴ

-0.13

POSITIVE LOGITS

querque

0.19

bish

0.17

ill

0.17

acier

0.17

abbo

0.16

con

0.15

geois

0.15

atorial

0.15

annt

0.14

selectedIndex

0.14

Activations Density 0.101%

specific names or references related to individuals or proper nouns

No Comments

No Known Activations