INDEX

Explanations

contractions indicating possession or associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

erb

-0.15

uir

-0.14

ocking

-0.14

oug

-0.14

-scrollbar

-0.14

 sáº¯c

-0.14

 Pike

-0.14

thon

-0.14

å¹

-0.14

Ryu

-0.13

POSITIVE LOGITS

go

0.16

imm

0.16

anos

0.15

_go

0.15

ibil

0.15

avor

0.15

igit

0.15

aves

0.14

elen

0.14

Activations Density 0.018%

contractions indicating possession or associations

No Comments

No Known Activations