INDEX

Explanations

occurrences of specific key terms related to inclusion and availability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

illon

-0.14

ord

-0.14

aug

-0.14

|{↵

-0.13

ipi

-0.13

ÏĩÎµ

-0.13

ÅĤaw

-0.13

ilder

-0.13

den

-0.13

pul

-0.13

POSITIVE LOGITS

åĪ¥

0.18

quam

0.17

ouble

0.16

 corners

0.16

imeType

0.16

arella

0.15

ropa

0.14

ulaire

0.14

atisfied

0.14

Activations Density 0.001%

occurrences of specific key terms related to inclusion and availability

No Comments

No Known Activations