INDEX

Explanations

negative sentiments or criticisms about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ï

-0.16

Ã³mo

-0.14

ongyang

-0.14

ï

-0.14

NOM

-0.14

eneric

-0.13

oro

-0.13

 æľ¬

-0.13

ippers

-0.13

 Lips

-0.13

POSITIVE LOGITS

agate

0.15

 harc

0.14

jav

0.14

stab

0.14

 Garr

0.13

dorf

0.13

à¤¾à¤Ĺà¤¤

0.13

 Å¡p

0.13

jis

0.13

USTOM

0.13

Activations Density 1.304%

negative sentiments or criticisms about various subjects

No Comments

No Known Activations