INDEX

Explanations

calls to action or invitations to participate in events or causes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ison

-0.16

anian

-0.16

anson

-0.15

ÙĨØ³

-0.15

 Manus

-0.14

 Sanity

-0.14

ÂŃi

-0.14

 verdict

-0.14

edian

-0.13

ubi

-0.13

POSITIVE LOGITS

ocator

0.15

Ł

0.14

 join

0.14

zf

0.14

ìļ´ëį°

0.14

 åı·

0.13

Ã¤ng

0.13

INCT

0.13

otto

0.13

Activations Density 0.106%

calls to action or invitations to participate in events or causes

No Comments

No Known Activations