INDEX

Explanations

references to concepts related to ineffective solutions or the consequences of actions

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

à¤¾à¤£

-0.15

oya

-0.15

ingham

-0.15

asher

-0.14

ozo

-0.14

 ÙĨØ¨

-0.14

Cly

-0.14

OLT

-0.14

Tpl

-0.14

 Tiny

-0.14

POSITIVE LOGITS

ÃĹ↵↵

0.18

 underground

0.17

 Vaults

0.15

_ue

0.15

 åł

0.15

åł

0.14

 defiance

0.14

iyel

0.14

ade

0.14

Activations Density 0.076%

references to concepts related to ineffective solutions or the consequences of actions

No Comments

No Known Activations