INDEX

Explanations

references to total quantities or amounts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

.SDK

-0.15

etc

-0.15

vÄĽt

-0.15

fell

-0.14

 Decompiled

-0.14

anda

-0.14

 Lump

-0.14

roma

-0.13

ãĤĢ

-0.13

POSITIVE LOGITS

tti

0.17

ti

0.17

ted

0.17

Corner

0.15

 Pace

0.15

phem

0.15

ihn

0.15

RequestMethod

0.15

 Corner

0.15

Smarty

0.14

Activations Density 0.015%

references to total quantities or amounts

No Comments

No Known Activations