INDEX

Explanations

instances of the word "te" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Permanent

-0.15

©

-0.15

ibus

-0.14

onec

-0.14

lius

-0.14

Æ°á»¡ng

-0.13

=Value

-0.13

à¸¸à¸Ľ

-0.13

(æľ¨

-0.13

 Permanent

-0.13

POSITIVE LOGITS

bÃ©

0.17

adÃŃ

0.16

 saving

0.15

oya

0.15

ichten

0.15

icie

0.14

zin

0.14

aqu

0.14

Activations Density 0.020%

instances of the word "te" in various contexts

No Comments

No Known Activations