INDEX

Explanations

names of authors and their associated publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

uddle

-0.17

 REPL

-0.15

werp

-0.14

 Fernando

-0.14

antry

-0.14

indo

-0.14

 Reed

-0.14

Bun

-0.13

.dispatchEvent

-0.13

agli

-0.13

POSITIVE LOGITS

 ÑĪÐ¸

0.15

):?>↵

0.14

 diseÃ±ador

0.14

_mob

0.14

portun

0.14

amus

0.14

 resil

0.14

zia

0.14

readcrumb

0.13

Activations Density 0.005%

names of authors and their associated publications

No Comments

No Known Activations