INDEX

Explanations

phrases that indicate a transition or change in state

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

roz

-0.16

lectic

-0.15

asma

-0.15

lator

-0.15

alc

-0.14

udget

-0.14

oup

-0.14

-0.13

heit

-0.13

_fragment

-0.13

POSITIVE LOGITS

.datatables

0.16

 Ø¥ÙĦÙī

0.15

poke

0.15

ori

0.14

iji

0.14

PIO

0.14

 RuntimeObject

0.14

ìł¤

0.14

edImage

0.14

PIO

0.14

Activations Density 0.029%

phrases that indicate a transition or change in state

No Comments

No Known Activations