INDEX

Explanations

concepts related to the evaluation of value and knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

illa

-0.17

olet

-0.17

 gratis

-0.15

ozem

-0.15

iren

-0.15

gratis

-0.15

inka

-0.15

icia

-0.14

leigh

-0.14

ille

-0.14

POSITIVE LOGITS

 Wing

0.15

 wing

0.15

NDER

0.15

pio

0.14

 Esper

0.14

urance

0.14

//------------------------------------------------------------------------------↵↵

0.14

lund

0.14

 branch

0.13

Activations Density 0.214%

concepts related to the evaluation of value and knowledge

No Comments

No Known Activations