INDEX

Explanations

references to data structures and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æī¬

-0.15

etary

-0.15

 ëĭ¤ìļ´ë°Ľê¸°

-0.14

 mastur

-0.14

	TokenName

-0.14

ÐµÑĤÑĮÑģÑı

-0.14

 caucus

-0.14

 à¹Ĩ

-0.14

@js

-0.13

pez

-0.13

POSITIVE LOGITS

 Copies

0.26

 copies

0.26

 copy

0.26

 Copy

0.25

 assignment

0.24

 copying

0.24

 Assignment

0.24

_copy

0.24

 shallow

0.24

Copy

0.23

Activations Density 0.076%

references to data structures and programming concepts

No Comments

No Known Activations