INDEX

Explanations

terms related to public relations and communications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ignon

-0.16

ë¡Ŀ

-0.15

een

-0.15

/pass

-0.14

cheng

-0.14

inois

-0.14

ongyang

-0.14

 borr

-0.14

 billig

-0.13

 Predictor

-0.13

POSITIVE LOGITS

/public

0.18

/mark

0.16

/Public

0.16

/media

0.15

oup

0.15

abant

0.14

PR

0.14

Ð½ÑĸÐ²ÐµÑĢ

0.14

morgan

0.14

acceptable

0.14

Activations Density 0.041%

terms related to public relations and communications

No Comments

No Known Activations