INDEX

Explanations

occurrences of the letter "N"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

eway

-0.17

inded

-0.16

ington

-0.16

rello

-0.15

INGTON

-0.15

ombs

-0.15

ÙĦØ§Ùģ

-0.15

ombre

-0.14

ode

-0.14

.cgi

-0.14

POSITIVE LOGITS

apa

0.24

atch

0.24

ant

0.22

iles

0.20

YS

0.20

Orth

0.19

dash

0.19

fld

0.19

ixa

0.19

ighth

0.19

Activations Density 0.029%

occurrences of the letter "N"

No Comments

No Known Activations