INDEX

Explanations

specific entities, names, or titles related to notable organizations or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lucent

-0.16

ãĥ³ãĤ¯

-0.15

è¢ĭ

-0.14

/Linux

-0.14

reh

-0.14

 vlak

-0.14

_fatal

-0.14

casting

-0.14

ATERIAL

-0.14

ovaly

-0.13

POSITIVE LOGITS

urette

0.18

(L

0.18

=L

0.16

 compreh

0.15

icrous

0.15

-l

0.14

/L

0.14

irie

0.14

arin

0.14

éĳ

0.14

Activations Density 0.888%

specific entities, names, or titles related to notable organizations or individuals

No Comments

No Known Activations