INDEX

Explanations

terms related to legal services and assistance

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

edis

-0.15

heading

-0.15

iegel

-0.15

esian

-0.15

earing

-0.14

jen

-0.14

Jug

-0.14

ouver

-0.14

 pyramid

-0.14

jee

-0.14

POSITIVE LOGITS

 Bend

0.15

íķŃ

0.14

ssa

0.14

atatype

0.14

 RÃ¼ck

0.14

 transparent

0.13

 Panda

0.13

no

0.13

prov

0.13

 transparency

0.13

Activations Density 0.207%

terms related to legal services and assistance

No Comments

No Known Activations