INDEX

Explanations

terms related to software support and compatibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

bst

-0.16

reich

-0.15

erland

-0.14

EditMode

-0.14

 cour

-0.14

orig

-0.14

indr

-0.14

 Slut

-0.14

lets

-0.13

ormal

-0.13

POSITIVE LOGITS

.operation

0.15

ERC

0.14

.dds

0.14

eza

0.14

 Ø§ÙĦØªÙĪ

0.14

kins

0.14

Ð»ÑĸÑĤ

0.14

*(*

0.14

rece

0.14

asca

0.14

Activations Density 0.036%

terms related to software support and compatibility

No Comments

No Known Activations