INDEX

Explanations

technical terminology and structures related to data and event management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.16

DY

-0.14

SX

-0.14

_GRE

-0.14

inia

-0.14

_:

-0.13

antee

-0.13

.CommandType

-0.13

ush

-0.13

ava

-0.13

POSITIVE LOGITS

::

0.23

.new

0.21

ãĥ³ãĥĢ

0.16

::{

0.15

abcdefghijklmnop

0.15

nev

0.15

new

0.15

abcdefghijkl

0.15

oken

0.15

::↵

0.15

Activations Density 0.011%

technical terminology and structures related to data and event management

No Comments

No Known Activations