INDEX

Explanations

phrases related to conditions and uncertainties in situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ieres

-0.14

 onDataChange

-0.14

aje

-0.13

utin

-0.13

ãģ¹ãģį

-0.13

ajÄħc

-0.13

 __("

-0.13

ãĥ¬ãĥĥãĥĪ

-0.13

oras

-0.12

_DEPRECATED

-0.12

POSITIVE LOGITS

 there

0.25

 many

0.20

 some

0.18

there

0.17

many

0.15

 several

0.15

 they

0.14

áº¬

0.14

 neither

0.14

it

0.14

Activations Density 0.584%

phrases related to conditions and uncertainties in situations

No Comments

No Known Activations