INDEX

Explanations

dates and references to time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

afi

-0.18

eper

-0.16

åĪº

-0.14

edelta

-0.14

odge

-0.14

odor

-0.13

-Ñħ

-0.13

pear

-0.13

anya

-0.13

imes

-0.13

POSITIVE LOGITS

tbl

0.15

 stip

0.15

HAND

0.14

 âĢł

0.14

kem

0.14

ï¼īãģ¯

0.14

eriod

0.14

 died

0.14

mgr

0.14

riday

0.14

Activations Density 0.025%

dates and references to time periods

No Comments

No Known Activations