INDEX

Explanations

phrases and concepts related to definitions and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ayah

-0.14

–

-0.14

 Truy

-0.13

ongyang

-0.12

eah

-0.12

 especially

-0.12

eshire

-0.12

andra

-0.12

icensed

-0.12

ltk

-0.12

POSITIVE LOGITS

ÐµÐºÑĥ

0.15

ivre

0.14

Ð»Ð°Ð³Ð°

0.14

-toggler

0.13

Ð»Ð¾Ð¶

0.13

_UNSIGNED

0.12

roit

0.12

ÑĢÐµÐ¶

0.12

alar

0.12

Ì§

0.12

Activations Density 0.040%

phrases and concepts related to definitions and classifications

No Comments

No Known Activations