INDEX

Explanations

references to a specific magazine or publication and its audience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

teri

-0.16

µ

-0.16

URT

-0.15

icl

-0.15

 Stra

-0.14

htar

-0.14

ÅĻe

-0.14

YY

-0.14

vrier

-0.14

ê²½ê¸°

-0.14

POSITIVE LOGITS

Od

0.25

à

0.20

od

0.20

Od

0.20

.od

0.19

 à¤ľà¤Ĺ

0.17

ahoo

0.17

 Dash

0.16

_od

0.16

linger

0.16

Activations Density 0.018%

references to a specific magazine or publication and its audience

No Comments

No Known Activations