INDEX

Explanations

references to specific numerical values or identifiers within 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

asjon

-0.15

Authorization

-0.15

wed

-0.14

iram

-0.14

_snd

-0.14

.hl

-0.14

reta

-0.14

estic

-0.13

ames

-0.13

UDGE

-0.13

POSITIVE LOGITS

cth

0.16

 Chung

0.15

.hw

0.14

 chÃŃ

0.14

oux

0.14

ust

0.14

iez

0.14

 POLIT

0.14

 cabinet

0.13

 èĹ¤

0.13

Activations Density 0.000%

references to specific numerical values or identifiers within a technical context

No Comments

No Known Activations