INDEX

Explanations

references to companies and their stock market identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÑĥÑģÐ°

-0.16

kus

-0.14

anon

-0.14

poon

-0.14

afort

-0.14

.records

-0.14

_deinit

-0.13

.Framework

-0.13

imm

-0.13

ÅĦ

-0.13

POSITIVE LOGITS

Hem

0.17

 Norm

0.15

norm

0.15

erp

0.14

hem

0.14

 norms

0.14

 norm

0.14

Ø§Ø

0.14

.sprites

0.14

Activations Density 0.013%

references to companies and their stock market identifiers

No Comments

No Known Activations