INDEX

Explanations

punctuation marks and their contextual significance in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

abus

-0.16

ither

-0.14

aya

-0.14

monic

-0.14

Wyn

-0.13

nome

-0.13

algo

-0.13

 einmal

-0.13

emb

-0.13

var

-0.13

POSITIVE LOGITS

etch

0.15

Ã©ry

0.15

tu

0.14

urs

0.14

ÑĪÐºÑĥ

0.14

lab

0.14

uckle

0.13

ETCH

0.13

tte

0.13

weeted

0.13

Activations Density 0.285%

punctuation marks and their contextual significance in the text

No Comments

No Known Activations