INDEX

Explanations

terminology related to filtering mechanisms and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ONTAL

-0.17

 Erick

-0.16

 Escorts

-0.14

ENA

-0.14

iales

-0.13

ìĬµ

-0.13

oline

-0.13

ots

-0.13

á»Ľ

-0.13

zc

-0.13

POSITIVE LOGITS

 element

1.02

 elements

0.92

 Element

0.84

element

0.82

-element

0.82

åħĥç´ł

0.80

 Elements

0.79

elements

0.79

Element

0.77

_element

0.76

Activations Density 0.404%

terminology related to filtering mechanisms and their characteristics

No Comments

No Known Activations