INDEX

Explanations

elements related to quality, maintenance, and preservation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.17

agle

-0.15

ı

-0.15

alla

-0.14

uben

-0.14

inya

-0.14

endar

-0.14

oningen

-0.14

ree

-0.14

dings

-0.13

POSITIVE LOGITS

 integrity

0.17

ahy

0.16

exact

0.15

plib

0.15

.mods

0.15

antan

0.15

entin

0.15

 exact

0.14

ajo

0.14

robe

0.14

Activations Density 0.277%

elements related to quality, maintenance, and preservation in various contexts

No Comments

No Known Activations