INDEX

Explanations

punctuation marks, particularly periods and commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ð¾Ð¿ÑĢÐ¸

-0.14

Md

-0.14

 ifndef

-0.14

anke

-0.14

gili

-0.13

ingly

-0.13

ouden

-0.13

pic

-0.13

otts

-0.13

ode

-0.13

POSITIVE LOGITS

.RemoveAll

0.15

 siÃªu

0.14

quare

0.14

alling

0.14

 Ø§ÙĦØ±ÙħØ²ÙĬØ©

0.14

://"

0.13

ORY

0.13

dao

0.13

RYPTO

0.12

Activations Density 0.017%

punctuation marks, particularly periods and commas

No Comments

No Known Activations