INDEX

Explanations

occurrences of the word "direct" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

icht

-0.15

ichten

-0.15

atics

-0.15

lum

-0.14

elder

-0.14

psc

-0.14

richt

-0.14

oen

-0.14

-ending

-0.14

Ã¨m

-0.14

POSITIVE LOGITS

 directly

0.24

direct

0.24

 direct

0.23

 DIRECT

0.20

 Direct

0.20

.Direct

0.20

Direct

0.20

-direct

0.19

ivity

0.18

DIRECT

0.18

Activations Density 0.044%

occurrences of the word "direct" and its variations

No Comments

No Known Activations