INDEX

Explanations

names of people or entities associated with a specific context, likely in narrative or commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

opsis

-0.20

 digest

-0.15

OCI

-0.15

atif

-0.14

 harmless

-0.14

abra

-0.14

utin

-0.14

APS

-0.14

QUIT

-0.14

.workspace

-0.14

POSITIVE LOGITS

achu

0.14

intree

0.14

KHR

0.13

 ÙĦØ¯ÙĬ

0.13

 Tang

0.13

è¡

0.13

App

0.13

 Cree

0.13

.Wait

0.13

 Friend

0.13

Activations Density 0.073%

names of people or entities associated with a specific context, likely in narrative or commentary

No Comments

No Known Activations