INDEX

Explanations

references to location and travel-related experiences

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

ÑĢÐ¸Ñĩ

-0.15

inu

-0.15

_ops

-0.14

rens

-0.14

anus

-0.14

_RW

-0.14

 Cutting

-0.14

thane

-0.14

__':č↵

-0.14

 Tune

-0.13

POSITIVE LOGITS

 according

0.18

according

0.17

 According

0.16

quette

0.15

According

0.15

 ranking

0.15

æĵļ

0.15

isure

0.15

æį®

0.15

Activations Density 0.277%

references to location and travel-related experiences

No Comments

No Known Activations