INDEX

Explanations

dates and years mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ãĥĶãĥ¼

-0.19

-0.17

-0.16

readcr

-0.16

-0.15

POSITIVE LOGITS

0.18

six

0.16

0.15

ouro

0.15

asn

0.15

ben

0.15

 earlier

0.14

 zero

0.14

Activations Density 0.078%

dates and years mentioned in the text

No Comments

No Known Activations