INDEX

Explanations

references to specific object properties in code

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

Gas

-0.15

ilden

-0.15

isten

-0.15

tu

-0.15

oose

-0.15

ingham

-0.15

 Hint

-0.14

Tu

-0.14

rxjs

-0.14

usan

-0.14

POSITIVE LOGITS

oÄŁ

0.17

ibri

0.15

encoded

0.14

Ã¶yle

0.14

sein

0.14

bol

0.14

olan

0.14

 \č↵

0.13

esis

0.13

Activations Density 0.090%

references to specific object properties in code

No Comments

No Known Activations