INDEX

Explanations

numerical data or time indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

owski

-0.16

 Pron

-0.15

locator

-0.15

.nlm

-0.14

cci

-0.14

Ð¾Ð³ÑĢÐ°Ð¼

-0.14

ortho

-0.14

.Bounds

-0.14

heet

-0.14

POSITIVE LOGITS

0.25

0.23

0.18

Ķ

0.18

asa

0.17

 Blake

0.17

0.16

ãĤ§

0.15

urga

0.15

Activations Density 0.070%

numerical data or time indicators

No Comments

No Known Activations