INDEX

Explanations

occurrences of numbers formatted in various ways

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

apper

-0.15

 Official

-0.15

Official

-0.14

´Ī

-0.14

 unlucky

-0.14

as

-0.14

Sag

-0.13

ker

-0.13

 official

-0.13

POSITIVE LOGITS

ensi

0.15

 Median

0.15

ForeColor

0.15

Median

0.15

 Rigidbody

0.14

bart

0.14

anou

0.14

ÑĸÑĹÐ²

0.14

RW

0.14

ï»¿#

0.13

Activations Density 0.006%

occurrences of numbers formatted in various ways

No Comments

No Known Activations