INDEX

Explanations

terms related to geographic or cultural identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Credit

-0.15

 revision

-0.15

 credit

-0.15

.KeyCode

-0.15

 Revision

-0.15

Ð¾Ð´Ð°ÑĢ

-0.14

cai

-0.14

usercontent

-0.14

reater

-0.14

 Spit

-0.14

POSITIVE LOGITS

 latin

0.22

 orth

0.20

 Orth

0.18

 latina

0.18

 substant

0.17

orth

0.17

 attest

0.17

ÙĦÙģ

0.16

 graf

0.16

forma

0.16

Activations Density 0.083%

terms related to geographic or cultural identities

No Comments

No Known Activations