INDEX

Explanations

numerical representations of words related to counting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iculture

-0.14

rt

-0.14

ent

-0.14

 |--------------------------------------------------------------------------↵

-0.14

ç¾½

-0.14

ics

-0.14

ebek

-0.13

idl

-0.13

ixels

-0.13

POSITIVE LOGITS

zers

0.16

 Giang

0.15

UGE

0.15

reesome

0.14

ToFront

0.14

Ð±ÑĥÑĢÐ³

0.13

.scalablytyped

0.13

hpp

0.13

Ð»ÑĥÐ³

0.13

NavController

0.13

Activations Density 0.005%

numerical representations of words related to counting

No Comments

No Known Activations