INDEX

Explanations

technical terms and data structures related to programming and coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

nan

-0.16

ewire

-0.14

ounder

-0.14

Ã©rc

-0.14

ickets

-0.14

estation

-0.14

nan

-0.14

erc

-0.14

ibri

-0.14

ertia

-0.14

POSITIVE LOGITS

Compat

0.17

gnore

0.16

ZONE

0.15

usi

0.15

ISIBLE

0.14

Tah

0.13

ides

0.13

 Lyons

0.13

ken

0.13

_EXTERNAL

0.13

Activations Density 0.236%

technical terms and data structures related to programming and coding

No Comments

No Known Activations