INDEX

Explanations

references to specific individuals and their relationships in the context of collaborations and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ascript

-0.16

akhir

-0.15

akh

-0.14

_TestCase

-0.14

ãĥ«ãĥķ

-0.14

POOL

-0.14

_GR

-0.13

ksen

-0.13

oten

-0.13

ÑĦÐ¾ÑĢÑĤ

-0.13

POSITIVE LOGITS

 Bowie

0.54

Zig

0.39

Bow

0.28

bow

0.27

 David

0.27

Bow

0.26

zig

0.26

bow

0.26

Ig

0.25

 Stard

0.23

Activations Density 0.039%

references to specific individuals and their relationships in the context of collaborations and conflicts

No Comments

No Known Activations