INDEX

Explanations

phrases indicating a relationship or connection between entities

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

 Swan

-0.15

 Diss

-0.15

side

-0.15

TON

-0.14

buster

-0.14

ON

-0.14

 side

-0.14

 shall

-0.14

ingham

-0.14

 Dice

-0.14

POSITIVE LOGITS

æ¤ľ

0.16

ihn

0.14

%)↵↵

0.14

 tÃ´

0.14

ierten

0.14

asco

0.14

çĪµ

0.14

emen

0.13

.synthetic

0.13

Activations Density 0.295%

phrases indicating a relationship or connection between entities

No Comments

No Known Activations