INDEX

Explanations

instances of the word "host" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uder

-0.17

illas

-0.17

zes

-0.16

 Earn

-0.14

illa

-0.14

Earn

-0.14

usk

-0.14

 burner

-0.14

 flux

-0.14

ately

-0.14

POSITIVE LOGITS

ilities

0.18

olland

0.15

ÏĥÏĥÎ±

0.15

pow

0.14

AGMA

0.14

igne

0.14

izoph

0.14

etz

0.14

Pow

0.14

ahl

0.14

Activations Density 0.018%

instances of the word "host" and its variations

No Comments

No Known Activations