INDEX

Explanations

terms and references related to geographic locations, particularly places starting with 'G'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

uce

-0.18

 guise

-0.16

_g

-0.15

Current

-0.15

ÎµÎ½

-0.14

exion

-0.14

loys

-0.14

 gentleman

-0.14

ym

-0.14

cg

-0.14

POSITIVE LOGITS

osate

0.18

reich

0.16

SSIP

0.16

 phÃ©p

0.16

Å¾el

0.16

zel

0.15

atemala

0.15

äºĪ

0.15

)frame

0.14

ospels

0.14

Activations Density 0.989%

terms and references related to geographic locations, particularly places starting with 'G'

No Comments

No Known Activations