INDEX

Explanations

references to jobs, obligations, and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oot

-0.16

athon

-0.15

riority

-0.15

rike

-0.15

iat

-0.15

eme

-0.15

atter

-0.15

èŃ°

-0.14

relude

-0.14

ij

-0.14

POSITIVE LOGITS

ez

0.19

ughs

0.16

xbd

0.15

tems

0.14

 Pods

0.14

urdu

0.14

edu

0.14

(ur

0.14

fully

0.14

Enumerator

0.14

Activations Density 0.010%

references to jobs, obligations, and responsibilities

No Comments

No Known Activations