INDEX

Explanations

time and location references, particularly in relation to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oub

-0.14

innen

-0.14

ŀ

-0.14

ãĥªãĥ¼

-0.14

ÑĢÐ°Ð½

-0.14

kle

-0.14

 overd

-0.14

.mi

-0.14

ubar

-0.14

ntax

-0.13

POSITIVE LOGITS

igers

0.15

ÐµÑĢÑĤÐ²

0.14

ined

0.14

poke

0.14

aga

0.14

RuntimeObject

0.13

ngr

0.13

school

0.13

okt

0.13

ì»¤

0.13

Activations Density 0.051%

time and location references, particularly in relation to events

No Comments

No Known Activations