INDEX

Explanations

statements or claims regarding facts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

IFT

-0.15

ÄĻk

-0.15

ivalent

-0.15

é£

-0.15

entiful

-0.15

nothrow

-0.14

ayacak

-0.14

_RESOURCES

-0.14

äºľ

-0.14

akra

-0.13

POSITIVE LOGITS

 even

0.18

0.15

 sogar

0.15

ored

0.15

 arguably

0.15

0.14

ually

0.14

Activations Density 0.031%

statements or claims regarding facts

No Comments

No Known Activations