INDEX

Explanations

references to legal proceedings and testimony

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Exercises

-0.16

alist

-0.15

 éŁ

-0.15

jon

-0.14

+Sans

-0.14

Dog

-0.13

ÑĢÐ¾Ð²Ð¸Ñĩ

-0.13

iman

-0.13

orney

-0.13

erto

-0.13

POSITIVE LOGITS

morgan

0.16

SessionFactory

0.15

Ã¥

0.15

 Revision

0.14

igin

0.14

ograd

0.14

 Fusion

0.14

pst

0.14

ÏĥÏĩ

0.14

pur

0.13

Activations Density 0.184%

references to legal proceedings and testimony

No Comments

No Known Activations