INDEX

Explanations

references to nodes and their hierarchical relationships in a data structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

-minded

-0.19

ner

-0.18

nga

-0.17

ebo

-0.17

bourg

-0.16

coni

-0.16

loh

-0.16

 Bold

-0.16

mino

-0.15

íģ¼

-0.15

POSITIVE LOGITS

fault

0.18

ules

0.17

_modules

0.17

cipher

0.17

bij

0.17

owner

0.16

hunter

0.15

hood

0.15

age

0.15

Ð»Ð¸Ñĩ

0.15

Activations Density 0.076%

references to nodes and their hierarchical relationships in a data structure

No Comments

No Known Activations