INDEX

Explanations

references to specific components or technologies in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ubar

-0.20

esta

-0.17

BarButton

-0.15

igned

-0.15

æ³³

-0.15

hou

-0.14

Hou

-0.14

æŃ©

-0.14

 Fulton

-0.14

itur

-0.14

POSITIVE LOGITS

_emails

0.16

atÃ¶r

0.15

ingham

0.15

leigh

0.15

LastError

0.15

zas

0.15

*sp

0.15

 Interr

0.14

iol

0.14

åĺ´

0.14

Activations Density 0.007%

references to specific components or technologies in a technical context

No Comments

No Known Activations