INDEX

Explanations

phrases related to the editing and publishing process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

rum

-0.15

Reporting

-0.14

qv

-0.14

ÑĢÐ°Ð±Ð°ÑĤ

-0.14

_MI

-0.13

anian

-0.13

upp

-0.13

tube

-0.13

rax

-0.13

ostÃŃ

-0.13

POSITIVE LOGITS

 proof

0.60

 Proof

0.49

proof

0.46

Proof

0.44

-proof

0.40

 proofs

0.40

_proof

0.39

 edit

0.29

 editing

0.29

-edit

0.27

Activations Density 0.161%

phrases related to the editing and publishing process

No Comments

No Known Activations

phrases related to the editing and publishing process

No Comments

No Known Activations