INDEX

Explanations

expressions of residential locations and living situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ombre

-0.17

ke

-0.15

Î¯Î¿ÏĤ

-0.15

izin

-0.15

ombres

-0.14

opc

-0.14

 sweep

-0.14

æİ¥

-0.14

 Background

-0.14

stp

-0.14

POSITIVE LOGITS

ATUS

0.15

ÑĤÑĮÑģÑı

0.15

.bpm

0.14

INAL

0.14

Ø·

0.14

 Meter

0.13

$__

0.13

resco

0.13

gev

0.13

ulu

0.13

Activations Density 0.029%

expressions of residential locations and living situations

No Comments

No Known Activations