INDEX

Explanations

numerical ratings or scores associated with various items or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

CFR

-0.16

los

-0.14

irebase

-0.14

å¤ªéĥİ

-0.14

abd

-0.14

_atomic

-0.13

.cz

-0.13

mand

-0.13

iou

-0.13

dfd

-0.13

POSITIVE LOGITS

pit

0.14

ikler

0.14

rogen

0.14

 Binder

0.14

bj

0.14

geh

0.14

pk

0.13

athi

0.13

endir

0.13

ELY

0.13

Activations Density 0.071%

numerical ratings or scores associated with various items or activities

No Comments

No Known Activations