INDEX

Explanations

words related to sound, particularly those associated with vocalizations or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ROL

-0.18

adero

-0.16

ynth

-0.16

krb

-0.15

leftright

-0.15

ë¹

-0.15

enschaft

-0.15

AXB

-0.15

cran

-0.14

ÑıÑĩ

-0.14

POSITIVE LOGITS

agr

0.28

urning

0.27

urn

0.27

alleng

0.26

ise

0.26

af

0.24

ort

0.24

om

0.24

ast

0.23

alk

0.23

Activations Density 0.016%

words related to sound, particularly those associated with vocalizations or expressions

No Comments

No Known Activations