INDEX

Explanations

specific terms and constructs related to programming and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ijo

-0.16

iasm

-0.15

angan

-0.15

UIT

-0.15

pio

-0.14

ambia

-0.14

stad

-0.14

vard

-0.14

ieux

-0.14

tex

-0.14

POSITIVE LOGITS

sole

0.18

ronym

0.16

afil

0.15

dro

0.15

ogle

0.15

des

0.15

 å¼

0.15

 currency

0.15

bay

0.14

 Fond

0.14

Activations Density 0.015%

specific terms and constructs related to programming and technical specifications

No Comments

No Known Activations