INDEX

Explanations

occurrences of related word fragments

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

 corrid

-0.17

 toggle

-0.15

TestFixture

-0.15

aire

-0.14

awl

-0.14

idor

-0.14

_opts

-0.14

afa

-0.14

ball

-0.14

ensing

-0.14

POSITIVE LOGITS

urf

0.15

ISA

0.15

 Sloan

0.14

ubat

0.13

.setPrototypeOf

0.13

bro

0.13

Bil

0.13

à¸¢à¸²à¸¢

0.13

BRO

0.13

ICollection

0.13

Activations Density 0.000%

occurrences of related word fragments

No Comments

No Known Activations