INDEX

Explanations

expressions related to mathematical estimates and bounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

GetPosition

-0.16

pio

-0.15

enda

-0.14

 Shard

-0.14

msg

-0.14

ensa

-0.14

 Aura

-0.14

avorites

-0.14

ildo

-0.14

byn

-0.14

POSITIVE LOGITS

oler

0.14

neh

0.14

ammer

0.14

ÑĢÐµÑĪ

0.14

mpr

0.14

BOSE

0.14

ÙĪÙĩ

0.14

rine

0.13

ÑĪÐºÐ¸

0.13

ì¹ĺ

0.13

Activations Density 0.242%

expressions related to mathematical estimates and bounds

No Comments

No Known Activations