INDEX

Explanations

references to physical contact or emotional connections

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

 MainAxisAlignment

-0.16

ernet

-0.15

.scalablytyped

-0.15

Å¡it

-0.15

horse

-0.14

stav

-0.14

enor

-0.14

Subview

-0.14

thag

-0.14

quo

-0.14

POSITIVE LOGITS

-touch

0.17

 Touch

0.17

 touch

0.17

 TOUCH

0.16

erson

0.15

(es

0.15

OOK

0.15

ively

0.15

olley

0.15

beck

0.15

Activations Density 0.032%

references to physical contact or emotional connections

No Comments

No Known Activations