INDEX

Explanations

references to sources and news outlets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

MainFrame

-0.16

elines

-0.15

_mp

-0.15

riv

-0.14

Ð¶Ð¸Ð²

-0.14

Ð¸ÑĤÐ¾Ð¼

-0.14

.timestamps

-0.14

iets

-0.14

ÐµÐ»Ð¸Ðº

-0.14

isma

-0.14

POSITIVE LOGITS

 stron

0.16

Äįan

0.15

 Laure

0.15

 lookout

0.14

McB

0.14

ITT

0.14

 luder

0.14

0.13

autos

0.13

 pornos

0.13

Activations Density 0.027%

references to sources and news outlets

No Comments

No Known Activations