INDEX

Explanations

instances of the letter 'P' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

meer

-0.17

df

-0.17

 Edison

-0.14

locator

-0.14

rior

-0.14

 Crossing

-0.14

arken

-0.14

Strict

-0.13

arto

-0.13

ages

-0.13

POSITIVE LOGITS

ictionary

0.23

optim

0.20

opt

0.20

WND

0.20

UNK

0.19

uss

0.19

ORN

0.19

ops

0.19

ETA

0.18

interested

0.18

Activations Density 0.036%

instances of the letter 'P' in various contexts

No Comments

No Known Activations