INDEX

Explanations

references to former positions or titles held by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

/Instruction

-0.15

-0.14

assadors

-0.14

ÃŃnu

-0.14

chein

-0.14

 Ð²Ð½Ñĥ

-0.14

daq

-0.14

maz

-0.14

 maturity

-0.14

DNA

-0.14

POSITIVE LOGITS

cznie

0.15

eczy

0.14

gage

0.14

crit

0.14

 Crop

0.14

uer

0.13

elsif

0.13

Rab

0.13

-gl

0.13

ic

0.13

Activations Density 0.095%

references to former positions or titles held by individuals

No Comments

No Known Activations