INDEX

Explanations

technical and coding-related terminology within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

eru

-0.16

onne

-0.15

LOPT

-0.14

.setViewport

-0.14

BP

-0.14

/INFO

-0.14

ForResource

-0.14

FromClass

-0.14

 Lucky

-0.14

 cdecl

-0.13

POSITIVE LOGITS

CKET

0.16

SSION

0.15

hm

0.14

 pornstar

0.14

abus

0.14

isin

0.14

iente

0.14

 Strict

0.14

nger

0.14

_rewrite

0.13

Activations Density 0.193%

technical and coding-related terminology within the text

No Comments

No Known Activations