INDEX

Explanations

conjunctions and connections between ideas

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

 Ø§ÙĦØ³Ø¹ÙĪØ¯

-0.17

udades

-0.16

ÙĦÙĬÙĩ

-0.15

zl

-0.15

ensa

-0.15

isson

-0.14

amiliar

-0.14

thood

-0.14

MENT

-0.14

uren

-0.14

POSITIVE LOGITS

arb

0.16

 timed

0.15

anza

0.15

ieg

0.15

idge

0.14

 Revel

0.14

oft

0.14

ANTED

0.14

 Burgess

0.14

ÑģÐµÐ¼

0.14

Activations Density 0.204%

conjunctions and connections between ideas

No Comments

No Known Activations