INDEX

Explanations

references to specific film titles and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

asser

-0.14

Ð¾Ñı

-0.14

 Pale

-0.14

cis

-0.14

ÅĻet

-0.14

 Bent

-0.13

ebe

-0.13

gang

-0.13

thumb

-0.13

kav

-0.13

POSITIVE LOGITS

_ASM

0.17

 tiener

0.16

ModelIndex

0.16

 Observer

0.15

essler

0.15

rubu

0.15

.scalablytyped

0.14

ropol

0.14

ccion

0.14

Ð»Ð¸ÑĨ

0.14

Activations Density 0.003%

references to specific film titles and locations

No Comments

No Known Activations