INDEX

Explanations

references to the term "Dal" within 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lab

-0.16

ember

-0.15

ova

-0.15

le

-0.14

oval

-0.14

auga

-0.14

 __("

-0.14

&o

-0.14

tte

-0.13

POSITIVE LOGITS

Dal

0.20

ziel

0.20

Dal

0.19

adier

0.16

dal

0.16

Å¡ÃŃm

0.16

RK

0.15

tons

0.15

Ton

0.15

ergic

0.15

Activations Density 0.009%

references to the term "Dal" within various contexts

No Comments

No Known Activations