INDEX

Explanations

references to numerical rankings or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÑĭÐ»

-0.17

ãĥ«ãĥĪ

-0.15

\views

-0.15

 Celt

-0.14

obot

-0.14

ÐµÑĩ

-0.14

NOP

-0.14

antom

-0.14

:↵↵↵↵↵↵

-0.14

_blocking

-0.14

POSITIVE LOGITS

adan

0.15

 Prom

0.15

Î¬Î»

0.14

 Glover

0.14

cn

0.14

cha

0.14

åĬĽçļĦ

0.13

Ãºde

0.13

@s

0.13

Activations Density 0.031%

references to numerical rankings or statistics

No Comments

No Known Activations