INDEX

Explanations

references to popular media or social media engagement metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.17

-0.15

hait

-0.14

 Karlov

-0.14

unkt

-0.14

abcdefghijkl

-0.13

ads

-0.13

avou

-0.13

agnostic

-0.13

ode

-0.13

POSITIVE LOGITS

ModelError

0.17

 counting

0.14

lie

0.14

ilib

0.14

isz

0.14

.Native

0.14

isc

0.14

 à¤¹à¤ľ

0.14

wick

0.13

.Dark

0.13

Activations Density 0.037%

references to popular media or social media engagement metrics

No Comments

No Known Activations