INDEX

Explanations

references to ink or the act of writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

alet

-0.19

esty

-0.15

enne

-0.15

/back

-0.14

ibel

-0.14

aÃ§Ãµes

-0.14

raci

-0.14

ASHBOARD

-0.14

enn

-0.14

POSITIVE LOGITS

jet

0.25

ed

0.24

ling

0.20

ink

0.19

pen

0.19

edb

0.18

horn

0.18

ink

0.18

-paper

0.18

urious

0.17

Activations Density 0.008%

references to ink or the act of writing

No Comments

No Known Activations