INDEX

Explanations

references to fines and penalties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 long

-0.15

znik

-0.14

_DLL

-0.14

oog

-0.14

OfFile

-0.14

 Hedge

-0.14

PTY

-0.13

iet

-0.13

ãģķãĤĵ

-0.13

_stuff

-0.13

POSITIVE LOGITS

ring

0.16

áº¡n

0.15

 deton

0.14

 Antar

0.14

batch

0.14

vector

0.14

áº·ng

0.13

ias

0.13

 vect

0.13

(_:

0.13

Activations Density 0.012%

references to fines and penalties

No Comments

No Known Activations