INDEX

Explanations

references to instructions or steps in a DIY project

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

itech

-0.15

bris

-0.14

addField

-0.14

 Entries

-0.14

agr

-0.14

ror

-0.14

adge

-0.14

æĮ¯ãĤĬ

-0.13

itez

-0.13

mgr

-0.13

POSITIVE LOGITS

åľŃ

0.17

_pemb

0.15

ODO

0.14

 Rookie

0.14

PIP

0.14

@student

0.14

.Measure

0.13

niÅ¾

0.13

ORY

0.13

 ifndef

0.13

Activations Density 0.032%

references to instructions or steps in a DIY project

No Comments

No Known Activations