INDEX

Explanations

time indicators or timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

iders

-0.17

 Nicholson

-0.15

AILS

-0.15

Ñī

-0.15

memberOf

-0.14

cher

-0.14

herit

-0.14

å¸ģ

-0.14

ardon

-0.14

ipmap

-0.14

POSITIVE LOGITS

CT

0.17

èĸ¦

0.16

uentes

0.15

ET

0.15

istani

0.14

(stdin

0.14

ET

0.14

ursor

0.14

_initializer

0.14

VERTISEMENT

0.14

Activations Density 0.002%

time indicators or timestamps

No Comments

No Known Activations