INDEX

Explanations

temporal references and durations

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

ashi

-0.15

esen

-0.14

Fav

-0.14

 solder

-0.14

 Degrees

-0.14

visor

-0.14

ierrez

-0.14

meric

-0.14

ually

-0.13

POSITIVE LOGITS

cott

0.16

plat

0.15

datable

0.15

OffsetTable

0.15

eon

0.15

 qual

0.15

okino

0.14

 datatable

0.14

ownt

0.14

Isl

0.14

Activations Density 0.044%

temporal references and durations

No Comments

No Known Activations