INDEX

Explanations

references to analytics or evaluations of systems and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Å¾el

-0.17

emez

-0.16

kel

-0.15

YD

-0.15

 ÙħØ«ÙĦØ§

-0.14

Harness

-0.13

empo

-0.13

å¤©åłĤ

-0.13

uels

-0.13

.scalablytyped

-0.13

POSITIVE LOGITS

eken

0.15

anded

0.14

umu

0.14

...'

0.14

isia

0.14

ixed

0.13

/of

0.13

erer

0.13

‘

0.13

Activations Density 0.168%

references to analytics or evaluations of systems and structures

No Comments

No Known Activations