INDEX

Explanations

instances of public backlash or criticism related to various events 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Hedge

-0.16

ossa

-0.15

pur

-0.15

Ø§ÛĮØ´

-0.15

-0.14

reste

-0.14

 infring

-0.14

Ð°Ð»Ñĭ

-0.14

azzi

-0.14

OrElse

-0.14

POSITIVE LOGITS

olson

0.17

VML

0.17

INGLE

0.16

ogo

0.16

iri

0.15

-len

0.14

Ã«r

0.14

 tá»¥

0.14

 Marcos

0.13

apus

0.13

Activations Density 0.137%

instances of public backlash or criticism related to various events or individuals

No Comments

No Known Activations