INDEX

Explanations

affirmations or confirmations of statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ð¾Ñı

-0.18

 fark

-0.15

feld

-0.15

ondon

-0.14

upt

-0.14

èŃ·

-0.14

ÑĢÐ°Ðº

-0.13

 tang

-0.13

rg

-0.13

POSITIVE LOGITS

ãģ£ãģ±

0.16

datable

0.15

etas

0.15

 RedirectTo

0.15

olec

0.14

 Sawyer

0.14

peats

0.14

 bury

0.14

 æ¯

0.14

yes

0.14

Activations Density 0.027%

affirmations or confirmations of statements

No Comments

No Known Activations