INDEX

Explanations

conjunctions and variations of the word "and."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

iler

-0.17

ooks

-0.16

pri

-0.15

eln

-0.14

urt

-0.14

 ä»¶

-0.14

ugin

-0.14

mers

-0.14

ahan

-0.14

UGIN

-0.14

POSITIVE LOGITS

imity

0.15

arty

0.14

orts

0.14

rary

0.14

rez

0.14

azi

0.14

lector

0.13

wich

0.13

 Linear

0.13

Activations Density 0.139%

conjunctions and variations of the word "and."

No Comments

No Known Activations