INDEX

Explanations

requests for consultations and evaluations

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

)prepare

-0.18

actable

-0.15

èĪ¬

-0.15

ARDS

-0.14

aze

-0.14

edException

-0.14

ÃĹ↵↵

-0.14

uke

-0.14

ards

-0.14

Ã¨ve

-0.14

POSITIVE LOGITS

ÄħÅ¼

0.15

yro

0.15

ľ

0.14

 Dale

0.14

glass

0.14

oka

0.14

 glass

0.14

itas

0.14

-vis

0.13

 companions

0.13

Activations Density 0.698%

requests for consultations and evaluations

No Comments

No Known Activations