INDEX

Explanations

terms related to sequences and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

lix

-0.15

rav

-0.14

ê³Ħ

-0.14

uck

-0.14

Ø§Ø¦ÙĦØ©

-0.14

thers

-0.14

seg

-0.14

esso

-0.13

POSITIVE LOGITS

itous

0.17

eto

0.16

outh

0.15

hip

0.15

 generations

0.14

hood

0.14

ae

0.14

ë¬¼ìĿĦ

0.14

 Stre

0.14

NX

0.14

Activations Density 0.071%

terms related to sequences and consequences

No Comments

No Known Activations