INDEX

Explanations

programming constructs and functions related to matrix and array creation and manipulation

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

tick

-0.15

_orientation

-0.15

Ú¯ÙĦ

-0.14

etti

-0.13

Ã´le

-0.13

lem

-0.13

-await

-0.13

 Roose

-0.13

 ÙĪØ§Ø¨

-0.13

zem

-0.13

POSITIVE LOGITS

0.37

ÂłÂł

0.16

  ↵↵

0.15

Ãºc

0.15

↵

0.15

âĢĤ

0.15

0.14

 Âł

0.14

ruc

0.14

Activations Density 0.030%

programming constructs and functions related to matrix and array creation and manipulation

No Comments

No Known Activations