INDEX

Explanations

references to notable television shows or productions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

eto

-0.15

imeline

-0.14

tered

-0.14

 èĹ

-0.14

ï»¿#

-0.14

Spo

-0.13

æĹıèĩªæ²»

-0.13

ugi

-0.13

emos

-0.13

Advisor

-0.13

POSITIVE LOGITS

 prat

0.16

orre

0.15

umpt

0.14

 topl

0.14

AF

0.14

 tops

0.13

viz

0.13

Ð¶Ñĥ

0.13

 hereby

0.13

vis

0.13

Activations Density 0.000%

references to notable television shows or productions

No Comments

No Known Activations