INDEX

Explanations

references to the editing and publishing process in writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

_MI

-0.15

ury

-0.14

 dood

-0.13

.appendTo

-0.13

antis

-0.13

qv

-0.13

amba

-0.13

.MODE

-0.13

upp

-0.13

snap

-0.13

POSITIVE LOGITS

 proof

0.48

 Proof

0.40

proof

0.35

 proofs

0.35

Proof

0.35

_proof

0.34

-proof

0.30

 copy

0.27

 editorial

0.24

 edit

0.24

Activations Density 0.143%

references to the editing and publishing process in writing

No Comments

No Known Activations