INDEX

Explanations

terms related to legal actions and rights

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

odel

-0.19

ools

-0.14

èĮĥ

-0.14

 intents

-0.14

ag

-0.14

 Blades

-0.14

emed

-0.14

IMPLIED

-0.13

illon

-0.13

ence

-0.13

POSITIVE LOGITS

holm

0.19

 Complaint

0.17

 complaints

0.17

 relief

0.16

 dismissal

0.16

Fed

0.16

Dismiss

0.16

 complaint

0.16

pro

0.15

 dismissed

0.15

Activations Density 0.018%

terms related to legal actions and rights

No Comments

No Known Activations