INDEX

Explanations

temporal references indicating intervals of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

gnu

-0.17

 recently

-0.14

 Brew

-0.14

æ®¿

-0.14

gons

-0.14

ra

-0.14

aden

-0.14

nk

-0.13

modulo

-0.13

POSITIVE LOGITS

edl

0.16

icals

0.15

 Kurulu

0.14

aat

0.14

'gc

0.13

PERT

0.13

entifier

0.13

edm

0.13

 åĨ

0.13

words

0.13

Activations Density 0.026%

temporal references indicating intervals of time

No Comments

No Known Activations