INDEX

Explanations

references to initial public offerings (IPOs)

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

quartered

-0.15

ENC

-0.15

 Fell

-0.15

 Ð¸Ñģ

-0.14

.dylib

-0.14

 Schn

-0.14

å¿į

-0.14

bilder

-0.13

.pc

-0.13

CDATA

-0.13

POSITIVE LOGITS

alfa

0.16

emb

0.15

ÅĻi

0.15

0.14

Ń

0.14

GGLE

0.14

 Needle

0.14

 Seymour

0.14

atron

0.14

UTTON

0.14

Activations Density 0.002%

references to initial public offerings (IPOs)

No Comments

No Known Activations