INDEX

Explanations

references to privacy policies and changes to them

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

 láº«n

-0.15

uchs

-0.14

trag

-0.14

quipe

-0.14

Ã¼rlich

-0.14

-0.13

itez

-0.13

suppress

-0.13

 order

-0.13

POSITIVE LOGITS

antha

0.16

 incent

0.15

apan

0.15

_bindings

0.15

ROL

0.15

ÐºÐ¾Ð²Ð¾

0.14

annah

0.14

lige

0.14

ota

0.14

å¼ĺ

0.14

Activations Density 0.019%

references to privacy policies and changes to them

No Comments

No Known Activations