INDEX

Explanations

occurrences of legal and procedural language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

adio

-0.16

urus

-0.15

Å¼y

-0.14

.getSelection

-0.14

Cb

-0.14

hol

-0.14

_CB

-0.14

ãĤ¤ãĤ¯

-0.13

 DeÄŁ

-0.13

ocl

-0.13

POSITIVE LOGITS

amburg

0.15

idable

0.15

erto

0.15

vang

0.15

.Blocks

0.14

shima

0.14

cient

0.14

agh

0.14

imetype

0.14

NewItem

0.13

Activations Density 0.001%

occurrences of legal and procedural language

No Comments

No Known Activations