INDEX

Explanations

references to academic and educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ermo

-0.17

iasi

-0.16

ayd

-0.15

.wik

-0.15

vrier

-0.15

emade

-0.15

 Hooks

-0.14

idlo

-0.14

ertools

-0.14

Aws

-0.14

POSITIVE LOGITS

nel

0.16

nn

0.16

 transfers

0.15

lines

0.15

TC

0.14

italic

0.14

 optionally

0.14

 move

0.13

.OS

0.13

Activations Density 0.028%

references to academic and educational contexts

No Comments

No Known Activations