INDEX

Explanations

phrases indicating the presence of specific conditions or challenges within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ucker

-0.15

aga

-0.14

ÙĪØ³Øª

-0.13

é¸

-0.13

 Gallagher

-0.13

rsp

-0.13

Rif

-0.13

Î¼Î¹Ïĥ

-0.13

 Reverse

-0.13

cot

-0.13

POSITIVE LOGITS

ç»Ŀ

0.15

 ìłĪ

0.15

ÑĤÑİ

0.15

ushima

0.14

avenport

0.14

 Kramer

0.14

ulk

0.14

 Rosenberg

0.13

tparam

0.13

ceed

0.13

Activations Density 0.126%

phrases indicating the presence of specific conditions or challenges within a context

No Comments

No Known Activations