INDEX

Explanations

phrases indicating the presence or mention of legal or regulatory matters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

conte

-0.15

ffffffff

-0.15

_INCLUDED

-0.14

either

-0.14

azor

-0.14

ream

-0.14

odore

-0.14

[email

-0.14

 either

-0.13

endar

-0.13

POSITIVE LOGITS

 outright

0.18

 cáº£

0.17

0.16

 even

0.15

 ones

0.15

/full

0.15

éĢ£

0.14

ko

0.14

 sometimes

0.14

 some

0.14

Activations Density 0.136%

phrases indicating the presence or mention of legal or regulatory matters

No Comments

No Known Activations