INDEX

Explanations

information related to medical treatments and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Coord

-0.15

 Signup

-0.14

Dam

-0.14

AspNet

-0.14

 Krank

-0.14

ToLocal

-0.14

(.)

-0.14

isme

-0.13

tron

-0.13

 ÑģÐ»ÑĥÑĩ

-0.13

POSITIVE LOGITS

CHANT

0.17

akeup

0.16

 eskort

0.16

 tane

0.15

 toler

0.15

rosso

0.15

 equipo

0.15

 investigators

0.15

-REAL

0.15

ãĥ¥

0.14

Activations Density 0.009%

information related to medical treatments and their effects

No Comments

No Known Activations