INDEX

Explanations

occurrences of the word "has" and its variants 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

TRI

-0.14

erb

-0.14

æ´¾

-0.14

 ÑĤÑı

-0.14

geb

-0.14

erce

-0.13

uela

-0.13

ooky

-0.13

çĦ

-0.13

 Glam

-0.13

POSITIVE LOGITS

htags

0.17

htag

0.17

anken

0.16

sti

0.15

htub

0.15

lient

0.13

OwnProperty

0.13

Ú©Ø²

0.13

asio

0.13

dete

0.13

Activations Density 0.164%

occurrences of the word "has" and its variants in various contexts

No Comments

No Known Activations