INDEX

Explanations

references to common nouns and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

imbus

-0.18

-0.14

[âĢ¦

-0.13

Cly

-0.13

.mc

-0.13

.me

-0.13

.ls

-0.13

ãģĨãĤĵ

-0.13

 decrement

-0.13

POSITIVE LOGITS

opic

0.16

omorphic

0.16

zeit

0.15

Mob

0.15

ifice

0.14

ortic

0.14

lessly

0.14

gger

0.13

fter

0.13

 Moor

0.13

Activations Density 0.745%

references to common nouns and phrases

No Comments

No Known Activations