INDEX

Explanations

occurrences of the term "multi" or related prefixes, indicating a focus on multiplicity or diversity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

iÅ¡

-0.19

acic

-0.16

istrovstvÃŃ

-0.16

sher

-0.15

iyan

-0.15

ITTE

-0.15

mop

-0.15

jad

-0.15

ierte

-0.14

POSITIVE LOGITS

ilingual

0.35

ilateral

0.34

ivariate

0.33

itudes

0.32

ilater

0.28

ple

0.27

ivalent

0.26

iverse

0.25

nom

0.25

iband

0.24

Activations Density 0.010%

occurrences of the term "multi" or related prefixes, indicating a focus on multiplicity or diversity

No Comments

No Known Activations