INDEX

Explanations

expressions of requests for assistance or help

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

-0.14

mime

-0.14

eno

-0.14

meet

-0.14

Ð´Ð¸Ð½Ð°

-0.14

 commissions

-0.13

ilk

-0.13

raz

-0.13

ild

-0.13

Meet

-0.13

POSITIVE LOGITS

hab

0.16

ibase

0.15

-BEGIN

0.15

 Marl

0.15

awah

0.15

DDL

0.14

esel

0.14

tual

0.14

erland

0.14

EAR

0.14

Activations Density 0.031%

expressions of requests for assistance or help

No Comments

No Known Activations