INDEX

Explanations

punctuation marks, particularly periods

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

eda

-0.17

 Weed

-0.15

 bastard

-0.14

lie

-0.14

ch

-0.14

bia

-0.13

esp

-0.13

ãĥ³ãĤ°

-0.13

Ð¸ÑĢÐ¾Ð²

-0.13

studio

-0.13

POSITIVE LOGITS

nodoc

0.17

QRSTUV

0.15

ingham

0.15

Ð²ÐµÐ´Ð¸ÑĤÐµ

0.15

 åĶ

0.15

æ¼

0.14

á»ĳt

0.14

culo

0.14

adro

0.14

ONTAL

0.14

Activations Density 0.098%

punctuation marks, particularly periods

No Comments

No Known Activations