INDEX

Explanations

programming language syntax

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ailability

-0.17

weak

-0.15

ActivityResult

-0.15

erif

-0.15

ourd

-0.14

ioned

-0.14

*)_

-0.14

 stre

-0.14

antro

-0.14

spath

-0.13

POSITIVE LOGITS

ADDE

0.15

sis

0.14

lisi

0.14

ÑĢÑİ

0.14

@yahoo

0.14

ä¼

0.14

 sharpen

0.13

rum

0.13

bane

0.13

Activations Density 0.006%

programming language syntax

No Comments

No Known Activations