INDEX

Explanations

references to various types of facilities and their descriptions

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

ish

-0.16

nes

-0.16

nie

-0.15

zo

-0.15

ald

-0.15

ight

-0.15

light

-0.15

theid

-0.14

å¤ķ

-0.14

ÙĨØ¯Ùĩ

-0.14

POSITIVE LOGITS

arian

0.18

wap

0.15

ground

0.15

mente

0.15

iterals

0.15

usa

0.14

istic

0.14

urar

0.14

itarian

0.14

Activations Density 0.056%

references to various types of facilities and their descriptions

No Comments

No Known Activations