INDEX

Explanations

references to connections in programming, particularly related to database or network connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ung

-0.16

vor

-0.15

hev

-0.15

Ã©v

-0.15

 subst

-0.14

UNG

-0.14

éłĪ

-0.14

iedo

-0.14

ajo

-0.14

beth

-0.14

POSITIVE LOGITS

nist

0.16

osate

0.16

icut

0.16

 spare

0.15

InView

0.15

Scoped

0.15

 ç½

0.15

 Draco

0.14

Äįi

0.14

ELLOW

0.14

Activations Density 0.017%

references to connections in programming, particularly related to database or network connections

No Comments

No Known Activations