INDEX

Explanations

instances of the word "ach" and variations of the word "nach"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

itude

-0.19

pond

-0.15

 Humanities

-0.15

omb

-0.15

uju

-0.15

boro

-0.14

(Intent

-0.14

ermann

-0.14

pector

-0.14

 Jones

-0.14

POSITIVE LOGITS

azzi

0.18

alus

0.17

aben

0.14

ISR

0.14

urette

0.14

azio

0.14

vale

0.14

 Vend

0.14

TC

0.14

èĻĳ

0.14

Activations Density 0.006%

instances of the word "ach" and variations of the word "nach"

No Comments

No Known Activations