INDEX

Explanations

references to reality television shows, particularly involving the "Real Housewives" series

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

åĽ£

-0.18

oulos

-0.17

uchos

-0.15

oda

-0.15

leen

-0.14

subs

-0.14

 Grain

-0.13

cai

-0.13

ean

-0.13

æĻ´

-0.13

POSITIVE LOGITS

ocol

0.15

opak

0.14

INF

0.14

uder

0.14

/renderer

0.14

-et

0.14

APON

0.14

coc

0.14

.synthetic

0.13

Uns

0.13

Activations Density 0.008%

references to reality television shows, particularly involving the "Real Housewives" series

No Comments

No Known Activations