INDEX

Explanations

terms related to quantities and counts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ensa

-0.19

isko

-0.16

Ð½Ð¾ÑģÑıÑĤ

-0.15

asan

-0.15

 compl

-0.15

adin

-0.14

olare

-0.14

ones

-0.14

POSITIVE LOGITS

per

0.19

 available

0.18

 involved

0.18

idend

0.17

 needed

0.17

ativo

0.16

Ð°ÑĢÑĤ

0.16

arton

0.15

ailable

0.15

available

0.14

Activations Density 0.140%

terms related to quantities and counts in various contexts

No Comments

No Known Activations