INDEX

Explanations

programming-related commands and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Finds

-0.15

ze

-0.15

aver

-0.14

assa

-0.14

ses

-0.14

ham

-0.14

Ðº

-0.14

ENCED

-0.14

osten

-0.14

-0.13

POSITIVE LOGITS

egend

0.17

ynos

0.17

isci

0.16

asca

0.15

stance

0.15

ienes

0.15

Ã¡cil

0.15

bject

0.14

isContained

0.14

otine

0.14

Activations Density 0.053%

programming-related commands and structures

No Comments

No Known Activations