INDEX

Explanations

instances of specific entities or terms, particularly related to time or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

Ã³n

-0.19

lesi

-0.17

Ã¡i

-0.16

acia

-0.16

ersh

-0.16

atsby

-0.15

linger

-0.15

ÏĢÎµÎ¹

-0.15

Ð¾Ñĩ

-0.14

 stim

-0.14

POSITIVE LOGITS

ansen

0.21

ew

0.17

ollywood

0.17

igm

0.17

ambda

0.16

ush

0.16

eyn

0.16

kke

0.16

ANGED

0.15

Activations Density 0.010%

instances of specific entities or terms, particularly related to time or events

No Comments

No Known Activations