INDEX

Explanations

references to connection and relationships among individuals

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

izzle

-0.15

ãĥ¼ãĤº

-0.15

ucha

-0.14

azzi

-0.14

éļİ

-0.14

ocy

-0.14

PLOY

-0.14

baugh

-0.13

undle

-0.13

Ø·Ø©

-0.13

POSITIVE LOGITS

athi

0.15

.Bunifu

0.14

ÐµÑĢÑĤÐ²

0.14

Ð¾Ð»ÑĮÑĪ

0.14

amin

0.14

Jos

0.14

.ribbon

0.14

abr

0.14

 alguien

0.13

Activations Density 0.032%

references to connection and relationships among individuals

No Comments

No Known Activations