INDEX

Explanations

code-related syntax and structure

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

@student

-0.18

 Redistributions

-0.16

ABSPATH

-0.15

lund

-0.14

ÃŃna

-0.14

 surround

-0.14

@js

-0.14

 Surround

-0.13

 Gibbs

-0.13

 Niger

-0.13

POSITIVE LOGITS

Dit

0.21

 Similarly

0.19

 similarly

0.18

Similarly

0.18

 Likewise

0.17

ream

0.16

 Conversely

0.15

 another

0.15

oq

0.15

otel

0.14

Activations Density 0.168%

code-related syntax and structure

No Comments

No Known Activations