INDEX

Explanations

repetitions of the word "its" and variations in capitalization

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

COMPARE

-0.17

ALER

-0.17

istrator

-0.16

CDATA

-0.15

YTE

-0.15

infeld

-0.15

trag

-0.15

ÑĥÑĢÐ³

-0.15

Ø¬Ø§Ø¯

-0.15

icerca

-0.15

POSITIVE LOGITS

 lung

0.16

ai

0.15

ra

0.15

ch

0.15

0.14

creen

0.14

 Lung

0.14

Activations Density 0.031%

repetitions of the word "its" and variations in capitalization

No Comments

No Known Activations