INDEX

Explanations

representations of academic references and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

jk

-0.17

 Hutch

-0.15

_boost

-0.14

nici

-0.14

baÅŁ

-0.14

lichkeit

-0.14

aber

-0.14

 chaotic

-0.14

 wink

-0.14

 Bloody

-0.14

POSITIVE LOGITS

slack

0.20

 slack

0.17

:min

0.15

cone

0.15

 primal

0.15

 incumbent

0.15

 æĿ¾

0.15

 convex

0.14

 solver

0.14

 cone

0.14

Activations Density 0.015%

representations of academic references and citations

No Comments

No Known Activations